Remove posterior_transform from info-theoretic acquisition functions (#…

…2590)

Summary: Pull Request resolved: #2590

Differential Revision: D64698976

botorch/acquisition/input_constructors.py

@@ -1800,18 +1800,30 @@ def construct_inputs_qJES(
     model: Model,
     bounds: list[tuple[float, float]],
     num_optima: int = 64,
-    maximize: bool = True,
     condition_noiseless: bool = True,
+    maximize: bool = True,
     X_pending: Tensor | None = None,
     estimation_type: str = "LB",
     num_samples: int = 64,
 ):
     dtype = model.train_targets.dtype
+    if not maximize:
+        from botorch.acquisition.objective import LinearMCObjective
+
+        negating_objective = (
+            None
+            if maximize
+            else LinearMCObjective(weights=-torch.ones(model.num_outputs, dtype=dtype))
+        )
+    else:
+        negating_objective = None
+
     optimal_inputs, optimal_outputs = get_optimal_samples(
         model=model,
         bounds=torch.as_tensor(bounds, dtype=dtype).T,
         num_optima=num_optima,
-        maximize=maximize,
+        objective=negating_objective,
+        return_transformed=True,
     )
 
     inputs = {

botorch/acquisition/joint_entropy_search.py

@@ -28,7 +28,6 @@
 import torch
 from botorch import settings
 from botorch.acquisition.acquisition import AcquisitionFunction, MCSamplerMixin
-from botorch.acquisition.objective import PosteriorTransform
 
 from botorch.models.fully_bayesian import SaasFullyBayesianSingleTaskGP
 from botorch.models.gp_regression import MIN_INFERRED_NOISE_LEVEL
@@ -71,7 +70,6 @@ def __init__(
         optimal_inputs: Tensor,
         optimal_outputs: Tensor,
         condition_noiseless: bool = True,
-        posterior_transform: PosteriorTransform | None = None,
         X_pending: Tensor | None = None,
         estimation_type: str = "LB",
         maximize: bool = True,
@@ -95,9 +93,9 @@ def __init__(
                 estimate is computed: Lower bound" ("LB") or "Monte Carlo" ("MC").
                 Lower Bound is recommended due to the relatively high variance
                 of the MC estimator.
-            maximize: If true, we consider a maximization problem.
             X_pending: A `m x d`-dim Tensor of `m` design points that have been
                 submitted for function evaluation, but have not yet been evaluated.
+            maximize: If true, we consider a maximization problem.
             num_samples: The number of Monte Carlo samples used for the Monte Carlo
                 estimate.
         """
@@ -110,18 +108,17 @@ def __init__(
         # inputs come as num_optima_per_model x (num_models) x d
         # but we want it four-dimensional in the Fully bayesian case,
         # and three-dimensional otherwise.
-        self.optimal_inputs = optimal_inputs.unsqueeze(-2)
-        self.optimal_outputs = optimal_outputs.unsqueeze(-2)
-        self.posterior_transform = posterior_transform
-        self.maximize = maximize
-
         # The optima (can be maxima, can be minima) come in as the largest
         # values if we optimize, or the smallest (likely substantially negative)
         # if we minimize. Inside the acquisition function, however, we always
         # want to consider MAX-values. As such, we need to flip them if
         # we want to minimize.
+        self.maximize = maximize
         if not self.maximize:
             optimal_outputs = -optimal_outputs
+        self.optimal_inputs = optimal_inputs.unsqueeze(-2)
+        self.optimal_outputs = optimal_outputs.unsqueeze(-2)
+
         self.num_samples = optimal_inputs.shape[0]
         self.condition_noiseless = condition_noiseless
         self.initial_model = model
@@ -138,7 +135,8 @@ def __init__(
                 with settings.propagate_grads(False):
                     # We must do a forward pass one before conditioning.
                     self.initial_model.posterior(
-                        self.optimal_inputs[:1], observation_noise=False
+                        self.optimal_inputs[:1],
+                        observation_noise=False,
                     )
 
                 # This equates to the JES version proposed by Hvarfner et. al.
@@ -221,15 +219,15 @@ def _compute_lower_bound_information_gain(
 
         # Compute the mixture mean and variance
         posterior_m = self.conditional_model.posterior(
-            X.unsqueeze(MCMC_DIM), observation_noise=True
+            X.unsqueeze(MCMC_DIM),
+            observation_noise=True,
         )
         noiseless_var = self.conditional_model.posterior(
-            X.unsqueeze(MCMC_DIM), observation_noise=False
+            X.unsqueeze(MCMC_DIM),
+            observation_noise=False,
         ).variance
 
         mean_m = posterior_m.mean
-        if not self.maximize:
-            mean_m = -mean_m
         variance_m = posterior_m.variance
 
         check_no_nans(variance_m)
@@ -294,7 +292,10 @@ def _compute_monte_carlo_information_gain(
             A `batch_shape`-dim Tensor of acquisition values at the given design
             points `X`.
         """
-        initial_posterior = self.initial_model.posterior(X, observation_noise=True)
+        initial_posterior = self.initial_model.posterior(
+            X,
+            observation_noise=True,
+        )
 
         batch_shape = X.shape[:-2]
         sample_dim = len(batch_shape)
@@ -311,10 +312,12 @@ def _compute_monte_carlo_information_gain(
 
         # Compute the mixture mean and variance
         posterior_m = self.conditional_model.posterior(
-            X.unsqueeze(MCMC_DIM), observation_noise=True
+            X.unsqueeze(MCMC_DIM),
+            observation_noise=True,
         )
         noiseless_var = self.conditional_model.posterior(
-            X.unsqueeze(MCMC_DIM), observation_noise=False
+            X.unsqueeze(MCMC_DIM),
+            observation_noise=False,
         ).variance
 
         mean_m = posterior_m.mean

botorch_community/acquisition/input_constructors.py

@@ -17,6 +17,7 @@
 
 import torch
 from botorch.acquisition.input_constructors import acqf_input_constructor
+from botorch.acquisition.objective import LinearMCObjective
 from botorch.acquisition.utils import get_optimal_samples
 from botorch.models.model import Model
 from botorch_community.acquisition.bayesian_active_learning import (
@@ -68,13 +69,18 @@ def construct_inputs_SCoreBO(
 ):
     dtype = model.train_targets.dtype
     # the number of optima are per model
+    negating_objective = (
+        None
+        if maximize
+        else LinearMCObjective(weights=-torch.ones(model.num_outputs, dtype=dtype))
+    )
     optimal_inputs, optimal_outputs = get_optimal_samples(
         model=model,
         bounds=torch.as_tensor(bounds, dtype=dtype).T,
         num_optima=num_optima,
-        maximize=maximize,
+        objective=negating_objective,
+        return_transformed=True,
     )
-
     inputs = {
         "model": model,
         "optimal_inputs": optimal_inputs,