IaC-Eval and DPack (#278)

source/_data/SymbioticLab.bib

@@ -143,16 +143,16 @@ @InProceedings{hermes:sigcomm17
 In this paper, we introduce Hermes, a datacenter load balancer that is resilient to the aforementioned uncertainties. At its heart, Hermes leverages comprehensive sensing to detect path conditions including failures unattended before, and it reacts using timely yet cautious rerouting. Hermes is a practical edge-based solution with no switch modification. We have implemented Hermes with commodity switches and evaluated it through both testbed experiments and large-scale simulations. Our results show that Hermes achieves comparable performance to CONGA and Presto in normal cases, and well handles uncertainties: under asymmetries, Hermes achieves up to 10% and 20% better flow completion time (FCT) than CONGA and CLOVE; under switch failures, it outperforms all other schemes by over 32%.}
 }
 
-@InProceedings{frdma:kbnets2017,
+@InProceedings{frdma:kbnets17,
   Title                    = {Performance Isolation Anomalies in {RDMA}},
   Author                   = {Yiwen Zhang and Juncheng Gu and Youngmoon Lee and Mosharaf Chowdhury and Kang G. Shin},
   Booktitle                = {ACM SIGCOMMKBNets},
   Year                     = {2017},
   Month                    = {August},
 
   publist_confkey          = {KBNets'17},
-  publist_link             = {paper || frdma-kbnets2017.pdf},
-  publist_link             = {slides || frdma-kbnets2017-slides.pdf},
+  publist_link             = {paper || frdma-kbnets17.pdf},
+  publist_link             = {slides || frdma-kbnets17-slides.pdf},
   publist_topic = {Datacenter Networking},
   Abstract                 = {To meet the increasing throughput and latency demands of modern applications, many operators are rapidly deploying RDMA in their datacenters. At the same time, developers are re-designing their software to take advantage of RDMA's benefits for individual applications. However, when it comes to RDMA's performance, many simple questions remain open.
 
@@ -1891,3 +1891,15 @@ @article{pyxis:tpds
   publist_abstract = {
 Disaggregating compute from storage is an emerging trend in cloud computing. Effectively utilizing resources in both compute and storage pool is the key to high performance. The state-of-the-art scheduler provides optimal scheduling decisions for workloads with homogeneous tasks. However, cloud applications often generate a mix of tasks with diverse compute and IO characteristics, resulting in sub-optimal performance for existing solutions. We present Pyxis, a system that provides optimal scheduling decisions for mixed workloads in disaggregated datacenters with theoretical guarantees. Pyxis is capable of maximizing overall throughput while meeting latency SLOs. Pyxis decouples the scheduling of different tasks. Our insight is that the optimal solution has an “all-or-nothing” structure that can be captured by a single turning point in the spectrum of tasks. Based on task characteristics, the turning point partitions the tasks either all to storage nodes or all to compute nodes (none to storage nodes). We theoretically prove that the optimal solution has such a structure, and design an online algorithm with sub-second convergence. We implement a prototype of Pyxis. Experiments on CloudLab with various synthetic and application workloads show that Pyxis improves the throughput by 3–21× over the state-of-the-art solution.}
 }
+
+@InProceedings{dpack:eurosys25,
+  author    = {Pierre Tholoniat and Kelly Kostopoulou and Mosharaf Chowdhury and Asaf Cidon and Roxana Geambasu and Mathias Lécuyer and Junfeng Yang},
+  booktitle = {EuroSys},
+  title     = {{DPack}: Efficiency-Oriented Privacy Budget Scheduling},
+  year      = {2025},	
+  publist_confkey = {EuroSys'25},
+  publist_topic = {Systems + AI},
+  publist_link = {paper || dpack-eurosys25.pdf},
+  publist_abstract = {
+Machine learning (ML) models can leak information about users, and differential privacy (DP) provides a rigorous way to bound that leakage under a given budget. This DP budget can be regarded as a new type of compute resource in workloads of multiple ML models training on user data. Once it is used, the DP budget is forever consumed. Therefore, it is crucial to allocate it most efficiently to train as many models as possible. This paper presents a scheduler for privacy that optimizes for efficiency. We formulate privacy scheduling as a new type of multidimensional knapsack problem, called privacy knapsack, which maximizes DP budget efficiency. We show that privacy knapsack is NP-hard, hence practical algorithms are necessarily approximate. We develop an approximation algorithm for privacy knapsack, DPack, and evaluate it on microbenchmarks and on a new, synthetic private-ML workload we developed from the Alibaba ML cluster trace. We show that DPack: (1) often approaches the efficiency-optimal schedule, (2) consistently schedules more tasks compared to a state-of-the-art privacy scheduling algorithm that focused on fairness (1.3–1.7X in Alibaba, 1.0–2.6X in microbenchmarks), but (3) sacrifices some level of fairness for efficiency. Therefore, using DPack, DP ML operators should be able to train more models on the same amount of user data while offering the same privacy guarantee to their users.  }
+} 

source/_posts/IaC-Eval-Accepted-to-NeurIPS2024.md

@@ -0,0 +1,7 @@
+---
+title: IaC-Eval Accepted to Appear at NeurIPS'24. Congrats Jiachen!
+categories:
+  - News
+date: 2024-09-30 11:24:29
+tags:
+---

source/publications/index.md

@@ -131,6 +131,10 @@ venues:
   EuroSys:
     category: Conferences
     occurrences:
+    - key: EuroSys'25
+      name: The 20th European Conference on Computer Systems
+      date: 2025-03-30
+      url: https://2025.eurosys.org/
     - key: EuroSys'23
       name: The Eighteenth European Conference on Computer Systems
       date: 2023-05-08