From d0bf5fd842d56f31df4883a23cbb118adbf71df3 Mon Sep 17 00:00:00 2001
From: david-cortes <david.cortes.rivera@gmail.com>
Date: Sat, 14 Dec 2024 20:05:06 +0100
Subject: [PATCH] prefer descriptive parameter names

---
 R-package/R/callbacks.R                       | 32 +++++++----
 R-package/R/utils.R                           |  1 -
 R-package/R/xgb.Booster.R                     | 10 +---
 R-package/R/xgb.create.features.R             |  2 +-
 R-package/R/xgb.cv.R                          |  2 -
 R-package/R/xgb.dump.R                        |  1 -
 R-package/R/xgb.importance.R                  |  6 +-
 R-package/R/xgb.load.R                        |  1 -
 R-package/R/xgb.model.dt.tree.R               |  1 -
 R-package/R/xgb.plot.importance.R             |  1 -
 R-package/R/xgb.plot.multi.trees.R            |  2 +-
 R-package/R/xgb.plot.shap.R                   |  3 +-
 R-package/R/xgb.plot.tree.R                   |  1 -
 R-package/R/xgb.save.R                        |  1 -
 R-package/R/xgb.save.raw.R                    |  1 -
 R-package/R/xgb.train.R                       |  8 +--
 .../a-compatibility-note-for-saveRDS-save.Rd  |  1 -
 R-package/man/predict.xgb.Booster.Rd          |  3 -
 R-package/man/print.xgb.Booster.Rd            |  1 -
 R-package/man/print.xgb.cv.Rd                 |  1 -
 R-package/man/xgb.attr.Rd                     |  1 -
 R-package/man/xgb.cb.gblinear.history.Rd      | 32 +++++++----
 R-package/man/xgb.config.Rd                   |  1 -
 R-package/man/xgb.create.features.Rd          |  2 +-
 R-package/man/xgb.cv.Rd                       |  1 -
 R-package/man/xgb.dump.Rd                     |  1 -
 R-package/man/xgb.importance.Rd               |  6 +-
 R-package/man/xgb.load.Rd                     |  1 -
 R-package/man/xgb.model.dt.tree.Rd            |  1 -
 R-package/man/xgb.model.parameters.Rd         |  4 +-
 R-package/man/xgb.plot.importance.Rd          |  1 -
 R-package/man/xgb.plot.multi.trees.Rd         |  2 +-
 R-package/man/xgb.plot.shap.Rd                |  3 +-
 R-package/man/xgb.plot.tree.Rd                |  1 -
 R-package/man/xgb.save.Rd                     |  1 -
 R-package/man/xgb.save.raw.Rd                 |  1 -
 R-package/man/xgb.train.Rd                    |  8 +--
 R-package/tests/testthat/test_basic.R         | 55 ++++++++++++-------
 .../tests/testthat/test_booster_slicing.R     |  2 +-
 R-package/tests/testthat/test_callbacks.R     | 47 +++++++++-------
 .../tests/testthat/test_custom_objective.R    |  2 +-
 R-package/tests/testthat/test_glm.R           |  4 +-
 R-package/tests/testthat/test_helpers.R       | 25 ++++++---
 .../testthat/test_interaction_constraints.R   |  3 +-
 R-package/tests/testthat/test_interactions.R  | 14 ++++-
 R-package/tests/testthat/test_monotone.R      |  3 +-
 .../tests/testthat/test_parameter_exposure.R  |  4 +-
 .../tests/testthat/test_poisson_regression.R  |  4 +-
 R-package/tests/testthat/test_ranking.R       | 20 +++++--
 R-package/tests/testthat/test_unicode.R       |  2 +-
 R-package/tests/testthat/test_update.R        | 20 +++++--
 R-package/tests/testthat/test_xgboost.R       |  4 +-
 R-package/vignettes/discoverYourData.Rmd      |  2 +-
 R-package/vignettes/xgboostPresentation.Rmd   | 18 +++---
 54 files changed, 205 insertions(+), 170 deletions(-)

diff --git a/R-package/R/callbacks.R b/R-package/R/callbacks.R
index 961715a2e02e..aa8d85246c7e 100644
--- a/R-package/R/callbacks.R
+++ b/R-package/R/callbacks.R
@@ -960,17 +960,17 @@ xgb.cb.cv.predict <- function(save_models = FALSE, outputmargin = FALSE) {
 #'   booster = "gblinear",
 #'   objective = "reg:logistic",
 #'   eval_metric = "auc",
-#'   lambda = 0.0003,
-#'   alpha = 0.0003,
+#'   reg_lambda = 0.0003,
+#'   reg_alpha = 0.0003,
 #'   nthread = nthread
 #' )
 #'
-#' # For 'shotgun', which is a default linear updater, using high eta values may result in
+#' # For 'shotgun', which is a default linear updater, using high learning_rate values may result in
 #' # unstable behaviour in some datasets. With this simple dataset, however, the high learning
 #' # rate does not break the convergence, but allows us to illustrate the typical pattern of
 #' # "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
 #' bst <- xgb.train(
-#'   c(param, list(eta = 1.)),
+#'   c(param, list(learning_rate = 1.)),
 #'   dtrain,
 #'   evals = list(tr = dtrain),
 #'   nrounds = 200,
@@ -987,7 +987,7 @@ xgb.cb.cv.predict <- function(save_models = FALSE, outputmargin = FALSE) {
 #'   c(
 #'     param,
 #'     xgb.params(
-#'       eta = 0.8,
+#'       learning_rate = 0.8,
 #'       updater = "coord_descent",
 #'       feature_selector = "thrifty",
 #'       top_k = 1
@@ -1000,12 +1000,20 @@ xgb.cb.cv.predict <- function(save_models = FALSE, outputmargin = FALSE) {
 #' )
 #' matplot(xgb.gblinear.history(bst), type = "l")
 #' #  Componentwise boosting is known to have similar effect to Lasso regularization.
-#' # Try experimenting with various values of top_k, eta, nrounds,
+#' # Try experimenting with various values of top_k, learning_rate, nrounds,
 #' # as well as different feature_selectors.
 #'
 #' # For xgb.cv:
 #' bst <- xgb.cv(
-#'   c(param, list(eta = 0.8)),
+#'   c(
+#'     param,
+#'     xgb.params(
+#'       learning_rate = 0.8,
+#'       updater = "coord_descent",
+#'       feature_selector = "thrifty",
+#'       top_k = 1
+#'     )
+#'   ),
 #'   dtrain,
 #'   nfold = 5,
 #'   nrounds = 100,
@@ -1022,15 +1030,15 @@ xgb.cb.cv.predict <- function(save_models = FALSE, outputmargin = FALSE) {
 #'   booster = "gblinear",
 #'   objective = "multi:softprob",
 #'   num_class = 3,
-#'   lambda = 0.0003,
-#'   alpha = 0.0003,
+#'   reg_lambda = 0.0003,
+#'   reg_alpha = 0.0003,
 #'   nthread = nthread
 #' )
 #'
 #' # For the default linear updater 'shotgun' it sometimes is helpful
-#' # to use smaller eta to reduce instability
+#' # to use smaller learning_rate to reduce instability
 #' bst <- xgb.train(
-#'   c(param, list(eta = 0.5)),
+#'   c(param, list(learning_rate = 0.5)),
 #'   dtrain,
 #'   evals = list(tr = dtrain),
 #'   nrounds = 50,
@@ -1044,7 +1052,7 @@ xgb.cb.cv.predict <- function(save_models = FALSE, outputmargin = FALSE) {
 #'
 #' # CV:
 #' bst <- xgb.cv(
-#'   c(param, list(eta = 0.5)),
+#'   c(param, list(learning_rate = 0.5)),
 #'   dtrain,
 #'   nfold = 5,
 #'   nrounds = 70,
diff --git a/R-package/R/utils.R b/R-package/R/utils.R
index 81e15f7e4421..ab88ef5d58c1 100644
--- a/R-package/R/utils.R
+++ b/R-package/R/utils.R
@@ -493,7 +493,6 @@ NULL
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.Booster.R b/R-package/R/xgb.Booster.R
index 6ffaa299b500..e424d14d96cb 100644
--- a/R-package/R/xgb.Booster.R
+++ b/R-package/R/xgb.Booster.R
@@ -267,7 +267,6 @@ xgb.get.handle <- function(object) {
 #'   nrounds = 5,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 0.5,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
@@ -312,7 +311,6 @@ xgb.get.handle <- function(object) {
 #'   nrounds = 10,
 #'   params = xgb.params(
 #'     max_depth = 4,
-#'     eta = 0.5,
 #'     nthread = 2,
 #'     subsample = 0.5,
 #'     objective = "multi:softprob",
@@ -336,7 +334,6 @@ xgb.get.handle <- function(object) {
 #'   nrounds = 10,
 #'   params = xgb.params(
 #'     max_depth = 4,
-#'     eta = 0.5,
 #'     nthread = 2,
 #'     subsample = 0.5,
 #'     objective = "multi:softmax",
@@ -671,7 +668,6 @@ validate.features <- function(bst, newdata) {
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
@@ -779,7 +775,6 @@ xgb.attributes <- function(object) {
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
@@ -834,13 +829,13 @@ xgb.config <- function(object) {
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
+#'     learning_rate = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
 #' )
 #'
-#' xgb.model.parameters(bst) <- list(eta = 0.1)
+#' xgb.model.parameters(bst) <- list(learning_rate = 0.1)
 #'
 #' @rdname xgb.model.parameters
 #' @export
@@ -1281,7 +1276,6 @@ xgb.is.same.Booster <- function(obj1, obj2) {
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.create.features.R b/R-package/R/xgb.create.features.R
index 85d9d560cef0..a175e087945f 100644
--- a/R-package/R/xgb.create.features.R
+++ b/R-package/R/xgb.create.features.R
@@ -52,7 +52,7 @@
 #' dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 #' dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 #'
-#' param <- list(max_depth = 2, eta = 1, objective = 'binary:logistic', nthread = 1)
+#' param <- list(max_depth = 2, learning_rate = 1, objective = 'binary:logistic', nthread = 1)
 #' nrounds = 4
 #'
 #' bst <- xgb.train(params = param, data = dtrain, nrounds = nrounds)
diff --git a/R-package/R/xgb.cv.R b/R-package/R/xgb.cv.R
index 9b4095150117..2e22c1afc5ff 100644
--- a/R-package/R/xgb.cv.R
+++ b/R-package/R/xgb.cv.R
@@ -96,7 +96,6 @@
 #'   params = xgb.params(
 #'     nthread = 2,
 #'     max_depth = 3,
-#'     eta = 1,
 #'     objective = "binary:logistic"
 #'   ),
 #'   nfold = 5,
@@ -316,7 +315,6 @@ xgb.cv <- function(params = xgb.params(), data, nrounds, nfold,
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.dump.R b/R-package/R/xgb.dump.R
index cf601e6388c1..3560bf5dd180 100644
--- a/R-package/R/xgb.dump.R
+++ b/R-package/R/xgb.dump.R
@@ -34,7 +34,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.importance.R b/R-package/R/xgb.importance.R
index c1b45e81bb8c..d75d641a56f8 100644
--- a/R-package/R/xgb.importance.R
+++ b/R-package/R/xgb.importance.R
@@ -49,7 +49,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
@@ -63,7 +62,7 @@
 #'   nrounds = 20,
 #'   params = xgb.params(
 #'     booster = "gblinear",
-#'     eta = 0.3,
+#'     learning_rate = 0.3,
 #'     nthread = 1,
 #'     objective = "binary:logistic"
 #'   )
@@ -82,7 +81,6 @@
 #'   nrounds = nrounds,
 #'   params = xgb.params(
 #'     max_depth = 3,
-#'     eta = 0.2,
 #'     nthread = 2,
 #'     objective = "multi:softprob",
 #'     num_class = nclass
@@ -112,7 +110,7 @@
 #'   nrounds = 15,
 #'   params = xgb.params(
 #'     booster = "gblinear",
-#'     eta = 0.2,
+#'     learning_rate = 0.2,
 #'     nthread = 1,
 #'     objective = "multi:softprob",
 #'     num_class = nclass
diff --git a/R-package/R/xgb.load.R b/R-package/R/xgb.load.R
index b08a308a3dd8..1d7da333319b 100644
--- a/R-package/R/xgb.load.R
+++ b/R-package/R/xgb.load.R
@@ -35,7 +35,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.model.dt.tree.R b/R-package/R/xgb.model.dt.tree.R
index 12ed705ba8f7..d176c96ace3d 100644
--- a/R-package/R/xgb.model.dt.tree.R
+++ b/R-package/R/xgb.model.dt.tree.R
@@ -46,7 +46,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.plot.importance.R b/R-package/R/xgb.plot.importance.R
index 750f386dd6f2..8acec15a0dd5 100644
--- a/R-package/R/xgb.plot.importance.R
+++ b/R-package/R/xgb.plot.importance.R
@@ -55,7 +55,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 3,
-#'     eta = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.plot.multi.trees.R b/R-package/R/xgb.plot.multi.trees.R
index 1c57dd84babd..5b6764a6fdb4 100644
--- a/R-package/R/xgb.plot.multi.trees.R
+++ b/R-package/R/xgb.plot.multi.trees.R
@@ -40,7 +40,7 @@
 #'   verbose = 0,
 #'   params = xgb.params(
 #'     max_depth = 15,
-#'     eta = 1,
+#'     learning_rate = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic",
 #'     min_child_weight = 50
diff --git a/R-package/R/xgb.plot.shap.R b/R-package/R/xgb.plot.shap.R
index bb678968db88..5b0661dfea4b 100644
--- a/R-package/R/xgb.plot.shap.R
+++ b/R-package/R/xgb.plot.shap.R
@@ -86,7 +86,7 @@
 #'   nrounds = nrounds,
 #'   verbose = 0,
 #'   params = xgb.params(
-#'     eta = 0.1,
+#'     learning_rate = 0.1,
 #'     max_depth = 3,
 #'     subsample = 0.5,
 #'     objective = "binary:logistic",
@@ -114,7 +114,6 @@
 #'   verbose = 0,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 0.3,
 #'     subsample = 0.5,
 #'     nthread = nthread,
 #'     objective = "multi:softprob",
diff --git a/R-package/R/xgb.plot.tree.R b/R-package/R/xgb.plot.tree.R
index f18e17a9e1fe..86362f1c1659 100644
--- a/R-package/R/xgb.plot.tree.R
+++ b/R-package/R/xgb.plot.tree.R
@@ -44,7 +44,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 3,
-#'     eta = 1,
 #'     nthread = 2,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.save.R b/R-package/R/xgb.save.R
index 855cf964b37b..418b95f1d207 100644
--- a/R-package/R/xgb.save.R
+++ b/R-package/R/xgb.save.R
@@ -47,7 +47,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.save.raw.R b/R-package/R/xgb.save.raw.R
index 3c10cd9f2a5b..bd960de55738 100644
--- a/R-package/R/xgb.save.raw.R
+++ b/R-package/R/xgb.save.raw.R
@@ -26,7 +26,6 @@
 #'   nrounds = 2,
 #'   params = xgb.params(
 #'     max_depth = 2,
-#'     eta = 1,
 #'     nthread = nthread,
 #'     objective = "binary:logistic"
 #'   )
diff --git a/R-package/R/xgb.train.R b/R-package/R/xgb.train.R
index 9fe8fb3c8f29..cd13d82b172e 100644
--- a/R-package/R/xgb.train.R
+++ b/R-package/R/xgb.train.R
@@ -150,7 +150,6 @@
 #' ## A simple xgb.train example:
 #' param <- xgb.params(
 #'   max_depth = 2,
-#'   eta = 1,
 #'   nthread = nthread,
 #'   objective = "binary:logistic",
 #'   eval_metric = "auc"
@@ -176,7 +175,6 @@
 #' # 'eval_metric' parameters in the params list:
 #' param <- xgb.params(
 #'   max_depth = 2,
-#'   eta = 1,
 #'   nthread = nthread,
 #'   objective = logregobj,
 #'   eval_metric = evalerror
@@ -194,12 +192,12 @@
 #' ## An xgb.train example of using variable learning rates at each iteration:
 #' param <- xgb.params(
 #'   max_depth = 2,
-#'   eta = 1,
+#'   learning_rate = 1,
 #'   nthread = nthread,
 #'   objective = "binary:logistic",
 #'   eval_metric = "auc"
 #' )
-#' my_etas <- list(eta = c(0.5, 0.1))
+#' my_learning_rates <- list(learning_rate = c(0.5, 0.1))
 #'
 #' bst <- xgb.train(
 #'  param,
@@ -207,7 +205,7 @@
 #'  nrounds = 2,
 #'  evals = evals,
 #'  verbose = 0,
-#'  callbacks = list(xgb.cb.reset.parameters(my_etas))
+#'  callbacks = list(xgb.cb.reset.parameters(my_learning_rates))
 #' )
 #'
 #' ## Early stopping:
diff --git a/R-package/man/a-compatibility-note-for-saveRDS-save.Rd b/R-package/man/a-compatibility-note-for-saveRDS-save.Rd
index c4e9026d77f3..5820cd3acf5e 100644
--- a/R-package/man/a-compatibility-note-for-saveRDS-save.Rd
+++ b/R-package/man/a-compatibility-note-for-saveRDS-save.Rd
@@ -85,7 +85,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/predict.xgb.Booster.Rd b/R-package/man/predict.xgb.Booster.Rd
index 2ef3f1b4bf61..ee0307bf3f47 100644
--- a/R-package/man/predict.xgb.Booster.Rd
+++ b/R-package/man/predict.xgb.Booster.Rd
@@ -226,7 +226,6 @@ bst <- xgb.train(
   nrounds = 5,
   params = xgb.params(
     max_depth = 2,
-    eta = 0.5,
     nthread = nthread,
     objective = "binary:logistic"
   )
@@ -271,7 +270,6 @@ bst <- xgb.train(
   nrounds = 10,
   params = xgb.params(
     max_depth = 4,
-    eta = 0.5,
     nthread = 2,
     subsample = 0.5,
     objective = "multi:softprob",
@@ -295,7 +293,6 @@ bst <- xgb.train(
   nrounds = 10,
   params = xgb.params(
     max_depth = 4,
-    eta = 0.5,
     nthread = 2,
     subsample = 0.5,
     objective = "multi:softmax",
diff --git a/R-package/man/print.xgb.Booster.Rd b/R-package/man/print.xgb.Booster.Rd
index e797bd60f6d4..e70e9f622f1a 100644
--- a/R-package/man/print.xgb.Booster.Rd
+++ b/R-package/man/print.xgb.Booster.Rd
@@ -26,7 +26,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/print.xgb.cv.Rd b/R-package/man/print.xgb.cv.Rd
index a8c1d70ef4a7..80e67e8ffb23 100644
--- a/R-package/man/print.xgb.cv.Rd
+++ b/R-package/man/print.xgb.cv.Rd
@@ -30,7 +30,6 @@ cv <- xgb.cv(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.attr.Rd b/R-package/man/xgb.attr.Rd
index 015da9458b9b..36a570f1732f 100644
--- a/R-package/man/xgb.attr.Rd
+++ b/R-package/man/xgb.attr.Rd
@@ -69,7 +69,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.cb.gblinear.history.Rd b/R-package/man/xgb.cb.gblinear.history.Rd
index a5c6cd17a011..c8586bf23c90 100644
--- a/R-package/man/xgb.cb.gblinear.history.Rd
+++ b/R-package/man/xgb.cb.gblinear.history.Rd
@@ -63,17 +63,17 @@ param <- xgb.params(
   booster = "gblinear",
   objective = "reg:logistic",
   eval_metric = "auc",
-  lambda = 0.0003,
-  alpha = 0.0003,
+  reg_lambda = 0.0003,
+  reg_alpha = 0.0003,
   nthread = nthread
 )
 
-# For 'shotgun', which is a default linear updater, using high eta values may result in
+# For 'shotgun', which is a default linear updater, using high learning_rate values may result in
 # unstable behaviour in some datasets. With this simple dataset, however, the high learning
 # rate does not break the convergence, but allows us to illustrate the typical pattern of
 # "stochastic explosion" behaviour of this lock-free algorithm at early boosting iterations.
 bst <- xgb.train(
-  c(param, list(eta = 1.)),
+  c(param, list(learning_rate = 1.)),
   dtrain,
   evals = list(tr = dtrain),
   nrounds = 200,
@@ -90,7 +90,7 @@ bst <- xgb.train(
   c(
     param,
     xgb.params(
-      eta = 0.8,
+      learning_rate = 0.8,
       updater = "coord_descent",
       feature_selector = "thrifty",
       top_k = 1
@@ -103,12 +103,20 @@ bst <- xgb.train(
 )
 matplot(xgb.gblinear.history(bst), type = "l")
 #  Componentwise boosting is known to have similar effect to Lasso regularization.
-# Try experimenting with various values of top_k, eta, nrounds,
+# Try experimenting with various values of top_k, learning_rate, nrounds,
 # as well as different feature_selectors.
 
 # For xgb.cv:
 bst <- xgb.cv(
-  c(param, list(eta = 0.8)),
+  c(
+    param,
+    xgb.params(
+      learning_rate = 0.8,
+      updater = "coord_descent",
+      feature_selector = "thrifty",
+      top_k = 1
+    )
+  ),
   dtrain,
   nfold = 5,
   nrounds = 100,
@@ -125,15 +133,15 @@ param <- xgb.params(
   booster = "gblinear",
   objective = "multi:softprob",
   num_class = 3,
-  lambda = 0.0003,
-  alpha = 0.0003,
+  reg_lambda = 0.0003,
+  reg_alpha = 0.0003,
   nthread = nthread
 )
 
 # For the default linear updater 'shotgun' it sometimes is helpful
-# to use smaller eta to reduce instability
+# to use smaller learning_rate to reduce instability
 bst <- xgb.train(
-  c(param, list(eta = 0.5)),
+  c(param, list(learning_rate = 0.5)),
   dtrain,
   evals = list(tr = dtrain),
   nrounds = 50,
@@ -147,7 +155,7 @@ matplot(xgb.gblinear.history(bst, class_index = 2), type = "l")
 
 # CV:
 bst <- xgb.cv(
-  c(param, list(eta = 0.5)),
+  c(param, list(learning_rate = 0.5)),
   dtrain,
   nfold = 5,
   nrounds = 70,
diff --git a/R-package/man/xgb.config.Rd b/R-package/man/xgb.config.Rd
index 12c23d2b29dd..1d199e8302d8 100644
--- a/R-package/man/xgb.config.Rd
+++ b/R-package/man/xgb.config.Rd
@@ -40,7 +40,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = nthread,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.create.features.Rd b/R-package/man/xgb.create.features.Rd
index ebb210435b43..1d6038df4436 100644
--- a/R-package/man/xgb.create.features.Rd
+++ b/R-package/man/xgb.create.features.Rd
@@ -62,7 +62,7 @@ data(agaricus.test, package = "xgboost")
 dtrain <- with(agaricus.train, xgb.DMatrix(data, label = label, nthread = 2))
 dtest <- with(agaricus.test, xgb.DMatrix(data, label = label, nthread = 2))
 
-param <- list(max_depth = 2, eta = 1, objective = 'binary:logistic', nthread = 1)
+param <- list(max_depth = 2, learning_rate = 1, objective = 'binary:logistic', nthread = 1)
 nrounds = 4
 
 bst <- xgb.train(params = param, data = dtrain, nrounds = nrounds)
diff --git a/R-package/man/xgb.cv.Rd b/R-package/man/xgb.cv.Rd
index 02a1a876b6a9..855781c0e53a 100644
--- a/R-package/man/xgb.cv.Rd
+++ b/R-package/man/xgb.cv.Rd
@@ -200,7 +200,6 @@ cv <- xgb.cv(
   params = xgb.params(
     nthread = 2,
     max_depth = 3,
-    eta = 1,
     objective = "binary:logistic"
   ),
   nfold = 5,
diff --git a/R-package/man/xgb.dump.Rd b/R-package/man/xgb.dump.Rd
index a3b622947eac..d10c61c46777 100644
--- a/R-package/man/xgb.dump.Rd
+++ b/R-package/man/xgb.dump.Rd
@@ -61,7 +61,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.importance.Rd b/R-package/man/xgb.importance.Rd
index f26067d7fef9..fe648cf8a639 100644
--- a/R-package/man/xgb.importance.Rd
+++ b/R-package/man/xgb.importance.Rd
@@ -75,7 +75,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
@@ -89,7 +88,7 @@ bst <- xgb.train(
   nrounds = 20,
   params = xgb.params(
     booster = "gblinear",
-    eta = 0.3,
+    learning_rate = 0.3,
     nthread = 1,
     objective = "binary:logistic"
   )
@@ -108,7 +107,6 @@ mbst <- xgb.train(
   nrounds = nrounds,
   params = xgb.params(
     max_depth = 3,
-    eta = 0.2,
     nthread = 2,
     objective = "multi:softprob",
     num_class = nclass
@@ -138,7 +136,7 @@ mbst <- xgb.train(
   nrounds = 15,
   params = xgb.params(
     booster = "gblinear",
-    eta = 0.2,
+    learning_rate = 0.2,
     nthread = 1,
     objective = "multi:softprob",
     num_class = nclass
diff --git a/R-package/man/xgb.load.Rd b/R-package/man/xgb.load.Rd
index 3059d530b017..ef546a30a178 100644
--- a/R-package/man/xgb.load.Rd
+++ b/R-package/man/xgb.load.Rd
@@ -41,7 +41,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = nthread,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.model.dt.tree.Rd b/R-package/man/xgb.model.dt.tree.Rd
index f55fc17a4e7b..d3c8c442d1b7 100644
--- a/R-package/man/xgb.model.dt.tree.Rd
+++ b/R-package/man/xgb.model.dt.tree.Rd
@@ -73,7 +73,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = nthread,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.model.parameters.Rd b/R-package/man/xgb.model.parameters.Rd
index 5f7c11a1eb95..53c0b60ca81b 100644
--- a/R-package/man/xgb.model.parameters.Rd
+++ b/R-package/man/xgb.model.parameters.Rd
@@ -39,12 +39,12 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
+    learning_rate = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
 )
 
-xgb.model.parameters(bst) <- list(eta = 0.1)
+xgb.model.parameters(bst) <- list(learning_rate = 0.1)
 
 }
diff --git a/R-package/man/xgb.plot.importance.Rd b/R-package/man/xgb.plot.importance.Rd
index 7b9dc40d2450..78ed27a22238 100644
--- a/R-package/man/xgb.plot.importance.Rd
+++ b/R-package/man/xgb.plot.importance.Rd
@@ -93,7 +93,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 3,
-    eta = 1,
     nthread = nthread,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.plot.multi.trees.Rd b/R-package/man/xgb.plot.multi.trees.Rd
index 989096e60e42..acea6ccd2d1b 100644
--- a/R-package/man/xgb.plot.multi.trees.Rd
+++ b/R-package/man/xgb.plot.multi.trees.Rd
@@ -74,7 +74,7 @@ bst <- xgb.train(
   verbose = 0,
   params = xgb.params(
     max_depth = 15,
-    eta = 1,
+    learning_rate = 1,
     nthread = nthread,
     objective = "binary:logistic",
     min_child_weight = 50
diff --git a/R-package/man/xgb.plot.shap.Rd b/R-package/man/xgb.plot.shap.Rd
index 7bdd5ad2bfac..471b5092f75c 100644
--- a/R-package/man/xgb.plot.shap.Rd
+++ b/R-package/man/xgb.plot.shap.Rd
@@ -139,7 +139,7 @@ bst <- xgb.train(
   nrounds = nrounds,
   verbose = 0,
   params = xgb.params(
-    eta = 0.1,
+    learning_rate = 0.1,
     max_depth = 3,
     subsample = 0.5,
     objective = "binary:logistic",
@@ -167,7 +167,6 @@ mbst <- xgb.train(
   verbose = 0,
   params = xgb.params(
     max_depth = 2,
-    eta = 0.3,
     subsample = 0.5,
     nthread = nthread,
     objective = "multi:softprob",
diff --git a/R-package/man/xgb.plot.tree.Rd b/R-package/man/xgb.plot.tree.Rd
index ebcc8603fe98..cafb8249c090 100644
--- a/R-package/man/xgb.plot.tree.Rd
+++ b/R-package/man/xgb.plot.tree.Rd
@@ -71,7 +71,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 3,
-    eta = 1,
     nthread = 2,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.save.Rd b/R-package/man/xgb.save.Rd
index 738f947405c7..65667b23291b 100644
--- a/R-package/man/xgb.save.Rd
+++ b/R-package/man/xgb.save.Rd
@@ -55,7 +55,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = nthread,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.save.raw.Rd b/R-package/man/xgb.save.raw.Rd
index 24f190a88c30..e881b9a7363f 100644
--- a/R-package/man/xgb.save.raw.Rd
+++ b/R-package/man/xgb.save.raw.Rd
@@ -37,7 +37,6 @@ bst <- xgb.train(
   nrounds = 2,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
     nthread = nthread,
     objective = "binary:logistic"
   )
diff --git a/R-package/man/xgb.train.Rd b/R-package/man/xgb.train.Rd
index 2a2d45c78924..ba2f4a9d884e 100644
--- a/R-package/man/xgb.train.Rd
+++ b/R-package/man/xgb.train.Rd
@@ -187,7 +187,6 @@ evals <- list(train = dtrain, eval = dtest)
 ## A simple xgb.train example:
 param <- xgb.params(
   max_depth = 2,
-  eta = 1,
   nthread = nthread,
   objective = "binary:logistic",
   eval_metric = "auc"
@@ -213,7 +212,6 @@ evalerror <- function(preds, dtrain) {
 # 'eval_metric' parameters in the params list:
 param <- xgb.params(
   max_depth = 2,
-  eta = 1,
   nthread = nthread,
   objective = logregobj,
   eval_metric = evalerror
@@ -231,12 +229,12 @@ bst <- xgb.train(
 ## An xgb.train example of using variable learning rates at each iteration:
 param <- xgb.params(
   max_depth = 2,
-  eta = 1,
+  learning_rate = 1,
   nthread = nthread,
   objective = "binary:logistic",
   eval_metric = "auc"
 )
-my_etas <- list(eta = c(0.5, 0.1))
+my_learning_rates <- list(learning_rate = c(0.5, 0.1))
 
 bst <- xgb.train(
  param,
@@ -244,7 +242,7 @@ bst <- xgb.train(
  nrounds = 2,
  evals = evals,
  verbose = 0,
- callbacks = list(xgb.cb.reset.parameters(my_etas))
+ callbacks = list(xgb.cb.reset.parameters(my_learning_rates))
 )
 
 ## Early stopping:
diff --git a/R-package/tests/testthat/test_basic.R b/R-package/tests/testthat/test_basic.R
index fdec78e88083..a12a30a0eeec 100644
--- a/R-package/tests/testthat/test_basic.R
+++ b/R-package/tests/testthat/test_basic.R
@@ -21,7 +21,7 @@ test_that("train and predict binary classification", {
       nrounds = nrounds,
       params = xgb.params(
         max_depth = 2,
-        eta = 1,
+        learning_rate = 1,
         nthread = n_threads,
         objective = "binary:logistic",
         eval_metric = "error"
@@ -116,7 +116,7 @@ test_that("dart prediction works", {
       booster = "dart",
       rate_drop = 0.5,
       one_drop = TRUE,
-      eta = 1,
+      learning_rate = 1,
       nthread = n_threads,
       objective = "reg:squarederror"
     )
@@ -134,7 +134,7 @@ test_that("dart prediction works", {
     params = xgb.params(
       booster = "dart",
       max_depth = 2,
-      eta = 1,
+      learning_rate = 1,
       rate_drop = 0.5,
       one_drop = TRUE,
       nthread = n_threads,
@@ -160,7 +160,7 @@ test_that("train and predict softprob", {
       data = xgb.DMatrix(as.matrix(iris[, -5]), label = lb),
       nrounds = 5,
       params = xgb.params(
-        max_depth = 3, eta = 0.5, nthread = n_threads,
+        max_depth = 3, learning_rate = 0.5, nthread = n_threads,
         objective = "multi:softprob", num_class = 3, eval_metric = "merror"
       ),
       evals = list(train = xgb.DMatrix(as.matrix(iris[, -5]), label = lb))
@@ -219,7 +219,7 @@ test_that("train and predict softmax", {
       data = xgb.DMatrix(as.matrix(iris[, -5]), label = lb),
       nrounds = 5,
       params = xgb.params(
-        max_depth = 3, eta = 0.5, nthread = n_threads,
+        max_depth = 3, learning_rate = 0.5, nthread = n_threads,
         objective = "multi:softmax", num_class = 3, eval_metric = "merror"
       ),
       evals = list(train = xgb.DMatrix(as.matrix(iris[, -5]), label = lb))
@@ -273,10 +273,15 @@ test_that("train and predict RF with softprob", {
     nrounds = nrounds,
     verbose = 0,
     params = xgb.params(
-      max_depth = 3, eta = 0.9, nthread = n_threads,
-      objective = "multi:softprob", eval_metric = "merror",
+      max_depth = 3,
+      learning_rate = 0.9,
+      nthread = n_threads,
+      objective = "multi:softprob",
+      eval_metric = "merror",
       num_class = 3,
-      num_parallel_tree = 4, subsample = 0.5, colsample_bytree = 0.5
+      num_parallel_tree = 4,
+      subsample = 0.5,
+      colsample_bytree = 0.5
     ),
     evals = list(train = xgb.DMatrix(as.matrix(iris[, -5]), label = lb))
   )
@@ -300,7 +305,7 @@ test_that("use of multiple eval metrics works", {
       nrounds = 2,
       params = list(
         max_depth = 2,
-        eta = 1, nthread = n_threads, objective = "binary:logistic",
+        learning_rate = 1, nthread = n_threads, objective = "binary:logistic",
         eval_metric = "error", eval_metric = "auc", eval_metric = "logloss"
       ),
       evals = list(train = xgb.DMatrix(train$data, label = train$label))
@@ -316,7 +321,9 @@ test_that("use of multiple eval metrics works", {
       nrounds = 2,
       params = xgb.params(
         max_depth = 2,
-        eta = 1, nthread = n_threads, objective = "binary:logistic",
+        learning_rate = 1,
+        nthread = n_threads,
+        objective = "binary:logistic",
         eval_metric = list("error", "auc", "logloss")
       ),
       evals = list(train = xgb.DMatrix(train$data, label = train$label))
@@ -333,7 +340,7 @@ test_that("training continuation works", {
   dtrain <- xgb.DMatrix(train$data, label = train$label, nthread = n_threads)
   evals <- list(train = dtrain)
   params <- xgb.params(
-    objective = "binary:logistic", max_depth = 2, eta = 1, nthread = n_threads
+    objective = "binary:logistic", max_depth = 2, learning_rate = 1, nthread = n_threads
   )
 
   # for the reference, use 4 iterations at once:
@@ -375,7 +382,9 @@ test_that("xgb.cv works", {
       nrounds = 2,
       params = xgb.params(
         max_depth = 2,
-        eta = 1., nthread = n_threads, objective = "binary:logistic",
+        learning_rate = 1.,
+        nthread = n_threads,
+        objective = "binary:logistic",
         eval_metric = "error"
       ),
       verbose = TRUE
@@ -402,7 +411,8 @@ test_that("xgb.cv works with stratified folds", {
     nfold = 5,
     params = xgb.params(
       max_depth = 2,
-      eta = 1., nthread = n_threads, objective = "binary:logistic"
+      nthread = n_threads,
+      objective = "binary:logistic"
     ),
     verbose = FALSE, stratified = FALSE
   )
@@ -413,7 +423,8 @@ test_that("xgb.cv works with stratified folds", {
     nrounds = 2,
     params = xgb.params(
       max_depth = 2,
-      eta = 1., nthread = n_threads, objective = "binary:logistic"
+      nthread = n_threads,
+      objective = "binary:logistic"
     ),
     verbose = FALSE, stratified = TRUE
   )
@@ -429,7 +440,8 @@ test_that("train and predict with non-strict classes", {
     nrounds = 2,
     params = xgb.params(
       max_depth = 2,
-      eta = 1, nthread = n_threads, objective = "binary:logistic"
+      nthread = n_threads,
+      objective = "binary:logistic"
     ),
     verbose = 0
   )
@@ -444,7 +456,8 @@ test_that("train and predict with non-strict classes", {
       nrounds = 2,
       params = xgb.params(
         max_depth = 2,
-        eta = 1, nthread = n_threads, objective = "binary:logistic"
+        nthread = n_threads,
+        objective = "binary:logistic"
       ),
       verbose = 0
     ),
@@ -462,7 +475,8 @@ test_that("train and predict with non-strict classes", {
       nrounds = 2,
       params = xgb.params(
         max_depth = 2,
-        eta = 1, nthread = n_threads, objective = "binary:logistic"
+        nthread = n_threads,
+        objective = "binary:logistic"
       ),
       verbose = 0
     ),
@@ -485,7 +499,7 @@ test_that("max_delta_step works", {
   params <- xgb.params(
     objective = "binary:logistic", eval_metric = "logloss", max_depth = 2,
     nthread = n_threads,
-    eta = 0.5
+    learning_rate = 0.5
   )
   nrounds <- 5
   # model with no restriction on max_delta_step
@@ -512,7 +526,7 @@ test_that("colsample_bytree works", {
   ## Use colsample_bytree = 0.01, so that roughly one out of 100 features is chosen for
   ## each tree
   params <- xgb.params(
-    max_depth = 2, eta = 0, nthread = n_threads,
+    max_depth = 2, learning_rate = 0, nthread = n_threads,
     colsample_bytree = 0.01, objective = "binary:logistic",
     eval_metric = "auc"
   )
@@ -530,7 +544,8 @@ test_that("Configuration works", {
     nrounds = 2,
     params = xgb.params(
       max_depth = 2,
-      eta = 1, nthread = n_threads, objective = "binary:logistic"
+      nthread = n_threads,
+      objective = "binary:logistic"
     )
   )
   config <- xgb.config(bst)
diff --git a/R-package/tests/testthat/test_booster_slicing.R b/R-package/tests/testthat/test_booster_slicing.R
index f80968e06476..d67e2f0b56ce 100644
--- a/R-package/tests/testthat/test_booster_slicing.R
+++ b/R-package/tests/testthat/test_booster_slicing.R
@@ -5,7 +5,7 @@ dm <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label, nthread = 1
 # Note: here need large step sizes in order for the predictions
 # to have substantially different leaf assignments on each tree
 model <- xgb.train(
-  params = list(objective = "binary:logistic", nthread = 1, max_depth = 4, eta = 0.5),
+  params = xgb.params(objective = "binary:logistic", nthread = 1, max_depth = 4),
   data = dm,
   nrounds = 20
 )
diff --git a/R-package/tests/testthat/test_callbacks.R b/R-package/tests/testthat/test_callbacks.R
index 7eef3cb46aa9..43fe56576d81 100644
--- a/R-package/tests/testthat/test_callbacks.R
+++ b/R-package/tests/testthat/test_callbacks.R
@@ -168,41 +168,41 @@ test_that("can store evaluation_log without printing", {
 
 test_that("xgb.cb.reset.parameters works as expected", {
 
-  # fixed eta
-  params <- c(params, list(eta = 0.9))
+  # fixed learning_rate
+  params <- c(params, list(learning_rate = 0.9))
   set.seed(111)
   bst0 <- xgb.train(params, dtrain, nrounds = 2, evals = evals, verbose = 0)
   expect_false(is.null(attributes(bst0)$evaluation_log))
   expect_false(is.null(attributes(bst0)$evaluation_log$train_error))
 
-  # same eta but re-set as a vector parameter in the callback
+  # same learning_rate but re-set as a vector parameter in the callback
   set.seed(111)
-  my_par <- list(eta = c(0.9, 0.9))
+  my_par <- list(learning_rate = c(0.9, 0.9))
   bst1 <- xgb.train(params, dtrain, nrounds = 2, evals = evals, verbose = 0,
                     callbacks = list(xgb.cb.reset.parameters(my_par)))
   expect_false(is.null(attributes(bst1)$evaluation_log$train_error))
   expect_equal(attributes(bst0)$evaluation_log$train_error,
                attributes(bst1)$evaluation_log$train_error)
 
-  # same eta but re-set via a function in the callback
+  # same learning_rate but re-set via a function in the callback
   set.seed(111)
-  my_par <- list(eta = function(itr, itr_end) 0.9)
+  my_par <- list(learning_rate = function(itr, itr_end) 0.9)
   bst2 <- xgb.train(params, dtrain, nrounds = 2, evals = evals, verbose = 0,
                     callbacks = list(xgb.cb.reset.parameters(my_par)))
   expect_false(is.null(attributes(bst2)$evaluation_log$train_error))
   expect_equal(attributes(bst0)$evaluation_log$train_error,
                attributes(bst2)$evaluation_log$train_error)
 
-  # different eta re-set as a vector parameter in the callback
+  # different learning_rate re-set as a vector parameter in the callback
   set.seed(111)
-  my_par <- list(eta = c(0.6, 0.5))
+  my_par <- list(learning_rate = c(0.6, 0.5))
   bst3 <- xgb.train(params, dtrain, nrounds = 2, evals = evals, verbose = 0,
                     callbacks = list(xgb.cb.reset.parameters(my_par)))
   expect_false(is.null(attributes(bst3)$evaluation_log$train_error))
   expect_false(all(attributes(bst0)$evaluation_log$train_error == attributes(bst3)$evaluation_log$train_error))
 
   # resetting multiple parameters at the same time runs with no error
-  my_par <- list(eta = c(1., 0.5), gamma = c(1, 2), max_depth = c(4, 8))
+  my_par <- list(learning_rate = c(1., 0.5), min_split_loss = c(1, 2), max_depth = c(4, 8))
   expect_error(
     bst4 <- xgb.train(params, dtrain, nrounds = 2, evals = evals, verbose = 0,
                       callbacks = list(xgb.cb.reset.parameters(my_par)))
@@ -214,7 +214,7 @@ test_that("xgb.cb.reset.parameters works as expected", {
   , NA) # NA = no error
 
   # expect no learning with 0 learning rate
-  my_par <- list(eta = c(0., 0.))
+  my_par <- list(learning_rate = c(0., 0.))
   bstX <- xgb.train(params, dtrain, nrounds = 2, evals = evals, verbose = 0,
                     callbacks = list(xgb.cb.reset.parameters(my_par)))
   expect_false(is.null(attributes(bstX)$evaluation_log$train_error))
@@ -255,7 +255,7 @@ test_that("xgb.cb.save.model works as expected", {
 })
 
 test_that("early stopping xgb.train works", {
-  params <- c(params, list(eta = 0.3))
+  params <- c(params, list(learning_rate = 0.3))
   set.seed(11)
   expect_output(
     bst <- xgb.train(params, dtrain, nrounds = 20, evals = evals,
@@ -292,7 +292,7 @@ test_that("early stopping using a specific metric works", {
       c(
         within(params, rm("eval_metric")),
         list(
-          eta = 0.6,
+          learning_rate = 0.6,
           eval_metric = "logloss",
           eval_metric = "auc"
         )
@@ -347,7 +347,7 @@ test_that("early stopping xgb.cv works", {
   expect_output(
     {
       cv <- xgb.cv(
-        c(params, list(eta = 0.3)),
+        c(params, list(learning_rate = 0.3)),
         dtrain,
         nfold = 5,
         nrounds = 20,
@@ -364,7 +364,7 @@ test_that("early stopping xgb.cv works", {
 })
 
 test_that("prediction in xgb.cv works", {
-  params <- c(params, list(eta = 0.5))
+  params <- c(params, list(learning_rate = 0.5))
   set.seed(11)
   nrounds <- 4
   cv <- xgb.cv(params, dtrain, nfold = 5, nrounds = nrounds, prediction = TRUE, verbose = 0)
@@ -386,7 +386,12 @@ test_that("prediction in xgb.cv works", {
 
 test_that("prediction in xgb.cv works for gblinear too", {
   set.seed(11)
-  p <- xgb.params(booster = 'gblinear', objective = "reg:logistic", eta = 0.5, nthread = n_threads)
+  p <- xgb.params(
+    booster = 'gblinear',
+    objective = "reg:logistic",
+    learning_rate = 0.5,
+    nthread = n_threads
+  )
   cv <- xgb.cv(p, dtrain, nfold = 5, nrounds = 2, prediction = TRUE, verbose = 0)
   expect_false(is.null(cv$evaluation_log))
   expect_false(is.null(cv$cv_predict$pred))
@@ -394,7 +399,7 @@ test_that("prediction in xgb.cv works for gblinear too", {
 })
 
 test_that("prediction in early-stopping xgb.cv works", {
-  params <- c(params, list(eta = 0.1, base_score = 0.5))
+  params <- c(params, list(learning_rate = 0.1, base_score = 0.5))
   set.seed(11)
   expect_output(
     cv <- xgb.cv(params, dtrain, nfold = 5, nrounds = 20,
@@ -425,9 +430,13 @@ test_that("prediction in xgb.cv for softprob works", {
         nfold = 4,
         nrounds = 5,
         params = xgb.params(
-          objective = "multi:softprob", num_class = 3,
-          eta = 0.5, max_depth = 3, nthread = n_threads,
-          subsample = 0.8, gamma = 2
+          objective = "multi:softprob",
+          num_class = 3,
+          learning_rate = 0.5,
+          max_depth = 3,
+          nthread = n_threads,
+          subsample = 0.8,
+          min_split_loss = 2
         ),
         verbose = 0,
         prediction = TRUE
diff --git a/R-package/tests/testthat/test_custom_objective.R b/R-package/tests/testthat/test_custom_objective.R
index 1d08b8ebf280..7c1dff8eb86b 100644
--- a/R-package/tests/testthat/test_custom_objective.R
+++ b/R-package/tests/testthat/test_custom_objective.R
@@ -28,7 +28,7 @@ evalerror <- function(preds, dtrain) {
   return(list(metric = "error", value = err))
 }
 
-param <- list(max_depth = 2, eta = 1, nthread = n_threads,
+param <- list(max_depth = 2, learning_rate = 1, nthread = n_threads,
               objective = logregobj, eval_metric = evalerror)
 num_round <- 2
 
diff --git a/R-package/tests/testthat/test_glm.R b/R-package/tests/testthat/test_glm.R
index 226439319dc8..89fcd98ebe1e 100644
--- a/R-package/tests/testthat/test_glm.R
+++ b/R-package/tests/testthat/test_glm.R
@@ -13,7 +13,7 @@ test_that("gblinear works", {
   )
 
   param <- list(objective = "binary:logistic", eval_metric = "error", booster = "gblinear",
-                nthread = n_threads, eta = 0.8, alpha = 0.0001, lambda = 0.0001)
+                nthread = n_threads, learning_rate = 0.8, reg_alpha = 0.0001, reg_lambda = 0.0001)
   evals <- list(eval = dtest, train = dtrain)
 
   n <- 5         # iterations
@@ -63,7 +63,7 @@ test_that("gblinear early stopping works", {
 
   param <- xgb.params(
     objective = "binary:logistic", eval_metric = "error", booster = "gblinear",
-    nthread = n_threads, eta = 0.8, alpha = 0.0001, lambda = 0.0001,
+    nthread = n_threads, learning_rate = 0.8, reg_alpha = 0.0001, reg_lambda = 0.0001,
     updater = "coord_descent"
   )
 
diff --git a/R-package/tests/testthat/test_helpers.R b/R-package/tests/testthat/test_helpers.R
index b03282cfd6d0..82b0279c4751 100644
--- a/R-package/tests/testthat/test_helpers.R
+++ b/R-package/tests/testthat/test_helpers.R
@@ -30,8 +30,10 @@ if (isTRUE(VCD_AVAILABLE)) {
       nrounds = nrounds, verbose = 0,
       params = xgb.params(
         max_depth = 9,
-        eta = 1, nthread = 2,
-        objective = "binary:logistic", booster = "gbtree",
+        learning_rate = 1,
+        nthread = 2,
+        objective = "binary:logistic",
+        booster = "gbtree",
         base_score = 0.5
       )
     )
@@ -40,8 +42,10 @@ if (isTRUE(VCD_AVAILABLE)) {
       data = xgb.DMatrix(sparse_matrix, label = label),
       nrounds = nrounds, verbose = 0,
       params = xgb.params(
-        eta = 1, nthread = 1,
-        objective = "binary:logistic", booster = "gblinear",
+        learning_rate = 1,
+        nthread = 1,
+        objective = "binary:logistic",
+        booster = "gblinear",
         base_score = 0.5
       )
     )
@@ -61,7 +65,7 @@ mbst.Tree <- xgb.train(
   verbose = 0,
   nrounds = nrounds,
   params = xgb.params(
-    max_depth = 3, eta = 0.5, nthread = 2,
+    max_depth = 3, learning_rate = 0.5, nthread = 2,
     objective = "multi:softprob", num_class = nclass, base_score = 0
   )
 )
@@ -71,7 +75,7 @@ mbst.GLM <- xgb.train(
   verbose = 0,
   nrounds = nrounds,
   params = xgb.params(
-    booster = "gblinear", eta = 0.1, nthread = 1,
+    booster = "gblinear", learning_rate = 0.1, nthread = 1,
     objective = "multi:softprob", num_class = nclass, base_score = 0
   )
 )
@@ -101,9 +105,11 @@ test_that("xgb.dump works for gblinear", {
     data = xgb.DMatrix(sparse_matrix, label = label),
     nrounds = 1,
     params = xgb.params(
-      eta = 1,
+      learning_rate = 1,
       nthread = 2,
-      alpha = 2, objective = "binary:logistic", booster = "gblinear"
+      reg_alpha = 2,
+      objective = "binary:logistic",
+      booster = "gblinear"
     )
   )
   d.sp <- xgb.dump(bst.GLM.sp)
@@ -420,7 +426,8 @@ test_that("xgb.model.dt.tree and xgb.importance work with a single split model",
     nrounds = 1, verbose = 0,
     params = xgb.params(
       max_depth = 1,
-      eta = 1, nthread = 2,
+      learning_rate = 1,
+      nthread = 2,
       objective = "binary:logistic"
     )
   )
diff --git a/R-package/tests/testthat/test_interaction_constraints.R b/R-package/tests/testthat/test_interaction_constraints.R
index d28f1e618d49..430b71a49bb4 100644
--- a/R-package/tests/testthat/test_interaction_constraints.R
+++ b/R-package/tests/testthat/test_interaction_constraints.R
@@ -18,7 +18,8 @@ test_that("interaction constraints for regression", {
     nrounds = 100, verbose = 0,
     params = xgb.params(
       max_depth = 3,
-      eta = 0.1, nthread = 2,
+      learning_rate = 0.1,
+      nthread = 2,
       interaction_constraints = list(c(0, 1))
     )
   )
diff --git a/R-package/tests/testthat/test_interactions.R b/R-package/tests/testthat/test_interactions.R
index a01adcc532d4..1325e73e4ea2 100644
--- a/R-package/tests/testthat/test_interactions.R
+++ b/R-package/tests/testthat/test_interactions.R
@@ -21,8 +21,12 @@ test_that("predict feature interactions works", {
   y <- f_int(X)
 
   dm <- xgb.DMatrix(X, label = y, nthread = n_threads)
-  param <- list(
-    eta = 0.1, max_depth = 4, base_score = mean(y), lambda = 0, nthread = n_threads
+  param <- xgb.params(
+    learning_rate = 0.1,
+    max_depth = 4,
+    base_score = mean(y),
+    reg_lambda = 0,
+    nthread = n_threads
   )
   b <- xgb.train(param, dm, 100)
 
@@ -124,7 +128,11 @@ test_that("multiclass feature interactions work", {
     as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1, nthread = n_threads
   )
   param <- xgb.params(
-    eta = 0.1, max_depth = 4, objective = 'multi:softprob', num_class = 3, nthread = n_threads
+    learning_rate = 0.1,
+    max_depth = 4,
+    objective = 'multi:softprob',
+    num_class = 3,
+    nthread = n_threads
   )
   b <- xgb.train(param, dm, 40)
   pred <- predict(b, dm, outputmargin = TRUE)
diff --git a/R-package/tests/testthat/test_monotone.R b/R-package/tests/testthat/test_monotone.R
index 70d67ceb7e22..e637f10590a9 100644
--- a/R-package/tests/testthat/test_monotone.R
+++ b/R-package/tests/testthat/test_monotone.R
@@ -12,7 +12,8 @@ test_that("monotone constraints for regression", {
         nrounds = 100, verbose = 0,
         params = xgb.params(
             max_depth = 2,
-            eta = 0.1, nthread = 2,
+            learning_rate = 0.1,
+            nthread = 2,
             monotone_constraints = -1
         )
     )
diff --git a/R-package/tests/testthat/test_parameter_exposure.R b/R-package/tests/testthat/test_parameter_exposure.R
index aacefe3a83ce..0d7c119090d0 100644
--- a/R-package/tests/testthat/test_parameter_exposure.R
+++ b/R-package/tests/testthat/test_parameter_exposure.R
@@ -16,7 +16,7 @@ bst <- xgb.train(
   nrounds = 10,
   params = xgb.params(
     max_depth = 2,
-    eta = 1,
+    learning_rate = 1,
     nthread = 1,
     objective = "binary:logistic"
   )
@@ -30,7 +30,7 @@ test_that("call is exposed to R", {
 test_that("params is exposed to R", {
   model_params <- attributes(bst)$params
   expect_is(model_params, "list")
-  expect_equal(model_params$eta, 1)
+  expect_equal(model_params$learning_rate, 1)
   expect_equal(model_params$max_depth, 2)
   expect_equal(model_params$objective, "binary:logistic")
 })
diff --git a/R-package/tests/testthat/test_poisson_regression.R b/R-package/tests/testthat/test_poisson_regression.R
index c045091d044b..c4caa7644a93 100644
--- a/R-package/tests/testthat/test_poisson_regression.R
+++ b/R-package/tests/testthat/test_poisson_regression.R
@@ -22,7 +22,7 @@ test_that("Poisson regression is centered around mean", {
   x <- matrix(rnorm(m * n), nrow = m)
   model <- xgb.train(
     data = xgb.DMatrix(x, label = y),
-    params = xgb.params(objective = "count:poisson", gamma = 1e4),
+    params = xgb.params(objective = "count:poisson", min_split_loss = 1e4),
     nrounds = 1
   )
   model_json <- xgb.save.raw(model, "json") |> rawToChar() |> jsonlite::fromJSON()
@@ -42,7 +42,7 @@ test_that("Poisson regression is centered around mean", {
   w <- y + 1
   model_weighted <- xgb.train(
     data = xgb.DMatrix(x, label = y, weight = w),
-    params = xgb.params(objective = "count:poisson", gamma = 1e4),
+    params = xgb.params(objective = "count:poisson", min_split_loss = 1e4),
     nrounds = 1
   )
   model_json <- xgb.save.raw(model_weighted, "json") |> rawToChar() |> jsonlite::fromJSON()
diff --git a/R-package/tests/testthat/test_ranking.R b/R-package/tests/testthat/test_ranking.R
index 3a87bc60944b..a7a55434a2fc 100644
--- a/R-package/tests/testthat/test_ranking.R
+++ b/R-package/tests/testthat/test_ranking.R
@@ -13,8 +13,14 @@ test_that('Test ranking with unweighted data', {
   group <- c(5, 5, 5, 5)
   dtrain <- xgb.DMatrix(X, label = y, group = group, nthread = n_threads)
 
-  params <- list(eta = 1, tree_method = 'exact', objective = 'rank:pairwise', max_depth = 1,
-                 eval_metric = 'auc', eval_metric = 'aucpr', nthread = n_threads)
+  params <- xgb.params(
+    learning_rate = 1,
+    tree_method = 'exact',
+    objective = 'rank:pairwise',
+    max_depth = 1,
+    eval_metric = c('auc', 'aucpr'),
+    nthread = n_threads
+  )
   bst <- xgb.train(params, dtrain, nrounds = 10, evals = list(train = dtrain), verbose = 0)
   # Check if the metric is monotone increasing
   expect_true(all(diff(attributes(bst)$evaluation_log$train_auc) >= 0))
@@ -35,9 +41,13 @@ test_that('Test ranking with weighted data', {
     X, label = y, group = group, weight = weight, nthread = n_threads
   )
 
-  params <- list(
-    eta = 1, tree_method = "exact", objective = "rank:pairwise", max_depth = 1,
-    eval_metric = "auc", eval_metric = "aucpr", nthread = n_threads
+  params <- xgb.params(
+    learning_rate = 1,
+    tree_method = "exact",
+    objective = "rank:pairwise",
+    max_depth = 1,
+    eval_metric = c("auc", "aucpr"),
+    nthread = n_threads
   )
   bst <- xgb.train(params, dtrain, nrounds = 10, evals = list(train = dtrain), verbose = 0)
   # Check if the metric is monotone increasing
diff --git a/R-package/tests/testthat/test_unicode.R b/R-package/tests/testthat/test_unicode.R
index efdb32ac31f3..6f34350d4242 100644
--- a/R-package/tests/testthat/test_unicode.R
+++ b/R-package/tests/testthat/test_unicode.R
@@ -13,7 +13,7 @@ test_that("Can save and load models with Unicode paths", {
     nrounds = nrounds,
     params = xgb.params(
       max_depth = 2,
-      eta = 1, nthread = 2,
+      nthread = 2,
       objective = "binary:logistic"
     )
   )
diff --git a/R-package/tests/testthat/test_update.R b/R-package/tests/testthat/test_update.R
index 7fdc6eb84bb3..899fca880050 100644
--- a/R-package/tests/testthat/test_update.R
+++ b/R-package/tests/testthat/test_update.R
@@ -20,8 +20,11 @@ test_that("updating the model works", {
   evals <- list(train = dtrain, test = dtest)
 
   # no-subsampling
-  p1 <- list(
-    objective = "binary:logistic", max_depth = 2, eta = 0.05, nthread = n_threads,
+  p1 <- xgb.params(
+    objective = "binary:logistic",
+    max_depth = 2,
+    learning_rate = 0.05,
+    nthread = n_threads,
     updater = "grow_colmaker,prune"
   )
   set.seed(11)
@@ -116,9 +119,16 @@ test_that("updating works for multiclass & multitree", {
     as.matrix(iris[, -5]), label = as.numeric(iris$Species) - 1, nthread = n_threads
   )
   evals <- list(train = dtr)
-  p0 <- list(max_depth = 2, eta = 0.5, nthread = n_threads, subsample = 0.6,
-             objective = "multi:softprob", num_class = 3, num_parallel_tree = 2,
-             base_score = 0)
+  p0 <- xgb.params(
+    max_depth = 2,
+    learning_rate = 0.5,
+    nthread = n_threads,
+    subsample = 0.6,
+    objective = "multi:softprob",
+    num_class = 3,
+    num_parallel_tree = 2,
+    base_score = 0
+  )
   set.seed(121)
   bst0 <- xgb.train(p0, dtr, 5, evals = evals, verbose = 0)
   tr0 <- xgb.model.dt.tree(model = bst0)
diff --git a/R-package/tests/testthat/test_xgboost.R b/R-package/tests/testthat/test_xgboost.R
index f3278cf37ea2..2e353e807c1d 100644
--- a/R-package/tests/testthat/test_xgboost.R
+++ b/R-package/tests/testthat/test_xgboost.R
@@ -595,7 +595,7 @@ test_that("Whole function works", {
     monotone_constraints = list(age = -1),
     nthreads = 1L,
     nrounds = 5L,
-    eta = 3
+    learning_rate = 3
   )
   expect_equal(
     attributes(model)$params$objective,
@@ -613,7 +613,7 @@ test_that("Whole function works", {
     "interaction_constraints" %in% names(attributes(model)$params)
   )
   expect_equal(
-    attributes(model)$params$eta,
+    attributes(model)$params$learning_rate,
     3
   )
   txt <- capture.output({
diff --git a/R-package/vignettes/discoverYourData.Rmd b/R-package/vignettes/discoverYourData.Rmd
index ed82e3b8ce49..8574dfe15b3e 100644
--- a/R-package/vignettes/discoverYourData.Rmd
+++ b/R-package/vignettes/discoverYourData.Rmd
@@ -174,7 +174,7 @@ The code below is very usual. For more information, you can look at the document
 
 ```{r}
 bst <- xgboost(x = sparse_matrix, y = output_vector,
-               max_depth = 4, eta = 1,
+               max_depth = 4, learning_rate = 1,
                nthread = 2, nrounds = 10)
 
 ```
diff --git a/R-package/vignettes/xgboostPresentation.Rmd b/R-package/vignettes/xgboostPresentation.Rmd
index 444f7ba96fa8..a3c61e3ab9ad 100644
--- a/R-package/vignettes/xgboostPresentation.Rmd
+++ b/R-package/vignettes/xgboostPresentation.Rmd
@@ -141,7 +141,7 @@ bstSparse <- xgboost(
     , y = factor(train$label, levels = c(0, 1))
     , objective = "binary:logistic"
     , max_depth = 2
-    , eta = 1
+    , learning_rate = 1
     , nrounds = 2
     , nthread = 2
 )
@@ -160,7 +160,7 @@ bstTrInterface <- xgb.train(
     , params = xgb.params(
         objective = "binary:logistic"
         , max_depth = 2
-        , eta = 1
+        , learning_rate = 1
         , nthread = 2
     )
     , nrounds = 2
@@ -183,7 +183,7 @@ bstDense <- xgboost(
     x = as.matrix(train$data),
     y = factor(train$label, levels = c(0, 1)),
     max_depth = 2,
-    eta = 1,
+    learning_rate = 1,
     nthread = 2,
     nrounds = 2
 )
@@ -200,7 +200,7 @@ bstDF <- xgboost(
     x = df_train,
     y = factor(train$label, levels = c(0, 1)),
     max_depth = 2,
-    eta = 1,
+    learning_rate = 1,
     nthread = 2,
     nrounds = 2
 )
@@ -222,7 +222,7 @@ bst <- xgboost(
     x = train$data,
     y = factor(train$label, levels = c(0, 1)),
     max_depth = 2,
-    eta = 1,
+    learning_rate = 1,
     nthread = 2,
     objective = "binary:logistic",
     nrounds = 5,
@@ -321,7 +321,7 @@ bst <- xgb.train(
     data = dtrain
     , params = list(
         max_depth = 2
-        , eta = 1
+        , learning_rate = 1
         , nthread = 2
         , objective = "binary:logistic"
     )
@@ -344,7 +344,7 @@ For a better understanding of the learning progression, you may want to have som
 bst <- xgb.train(
     data = dtrain
     , params = list(
-        eta = 1
+        learning_rate = 1
         , max_depth = 2
         , nthread = 2
         , objective = "binary:logistic"
@@ -361,7 +361,7 @@ bst <- xgb.train(
 ### Linear boosting
 
 
-Until now, all the learnings we have performed were based on boosting trees. **XGBoost** implements a second algorithm, based on linear boosting. The only difference with previous command is `booster = "gblinear"` parameter (and removing `eta` parameter).
+Until now, all the learnings we have performed were based on boosting trees. **XGBoost** implements a second algorithm, based on linear boosting. The only difference with previous command is `booster = "gblinear"` parameter (and removing `learning_rate` parameter).
 
 ```{r linearBoosting, message=F, warning=F}
 bst <- xgb.train(
@@ -398,7 +398,7 @@ bst <- xgb.train(
     data = dtrain2
     , params = list(
         max_depth = 2
-        , eta = 1
+        , learning_rate = 1
         , nthread = 2
         , objective = "binary:logistic"
     )