Closing the convergence gap of SGD without replacement

Mar 05, 2020
Shashank Rajput, Anant Gupta, Dimitris Papailiopoulos


  Access Model/Code and Paper
Federated Learning with Matched Averaging

Feb 15, 2020
Hongyi Wang, Mikhail Yurochkin, Yuekai Sun, Dimitris Papailiopoulos, Yasaman Khazaeni

* Accepted by ICLR 2020 

  Access Model/Code and Paper
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation

Jul 29, 2019
Shashank Rajput, Hongyi Wang, Zachary Charles, Dimitris Papailiopoulos


  Access Model/Code and Paper
Bad Global Minima Exist and SGD Can Reach Them

Jun 06, 2019
Shengchao Liu, Dimitris Papailiopoulos, Dimitris Achlioptas


  Access Model/Code and Paper
Convergence and Margin of Adversarial Training on Separable Data

May 22, 2019
Zachary Charles, Shashank Rajput, Stephen Wright, Dimitris Papailiopoulos


  Access Model/Code and Paper
Does Data Augmentation Lead to Positive Margin?

May 08, 2019
Shashank Rajput, Zhili Feng, Zachary Charles, Po-Ling Loh, Dimitris Papailiopoulos

* ICML 2019 

  Access Model/Code and Paper
SysML: The New Frontier of Machine Learning Systems

May 01, 2019
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Jennifer Chayes, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros Dimakis, Pradeep Dubey, Charles Elkan, Grigori Fursin, Gregory R. Ganger, Lise Getoor, Phillip B. Gibbons, Garth A. Gibson, Joseph E. Gonzalez, Justin Gottschlich, Song Han, Kim Hazelwood, Furong Huang, Martin Jaggi, Kevin Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konečný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Aparna Lakshmiratan, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Murray, Kunle Olukotun, Dimitris Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar


  Access Model/Code and Paper
ErasureHead: Distributed Gradient Descent without Delays Using Approximate Gradient Coding

Jan 28, 2019
Hongyi Wang, Zachary Charles, Dimitris Papailiopoulos


  Access Model/Code and Paper
A Geometric Perspective on the Transferability of Adversarial Directions

Nov 08, 2018
Zachary Charles, Harrison Rosenberg, Dimitris Papailiopoulos


  Access Model/Code and Paper
ATOMO: Communication-efficient Learning via Atomic Sparsification

Jun 24, 2018
Hongyi Wang, Scott Sievert, Shengchao Liu, Zachary Charles, Dimitris Papailiopoulos, Stephen Wright


  Access Model/Code and Paper
DRACO: Byzantine-resilient Distributed Training via Redundant Gradients

Jun 22, 2018
Lingjiao Chen, Hongyi Wang, Zachary Charles, Dimitris Papailiopoulos

* Accepted by ICML 2018 

  Access Model/Code and Paper
The Effect of Network Width on the Performance of Large-batch Training

Jun 11, 2018
Lingjiao Chen, Hongyi Wang, Jinman Zhao, Dimitris Papailiopoulos, Paraschos Koutris


  Access Model/Code and Paper
Gradient Coding via the Stochastic Block Model

May 25, 2018
Zachary Charles, Dimitris Papailiopoulos


  Access Model/Code and Paper
Speeding Up Distributed Machine Learning Using Codes

Jan 29, 2018
Kangwook Lee, Maximilian Lam, Ramtin Pedarsani, Dimitris Papailiopoulos, Kannan Ramchandran

* This work is published in IEEE Transactions on Information Theory and presented in part at the NIPS 2015 Workshop on Machine Learning Systems and the IEEE ISIT 2016 

  Access Model/Code and Paper
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning

Jan 07, 2018
Dong Yin, Ashwin Pananjady, Max Lam, Dimitris Papailiopoulos, Kannan Ramchandran, Peter Bartlett


  Access Model/Code and Paper
Approximate Gradient Coding via Sparse Random Graphs

Nov 17, 2017
Zachary Charles, Dimitris Papailiopoulos, Jordan Ellenberg


  Access Model/Code and Paper
Stability and Generalization of Learning Algorithms that Converge to Global Optima

Oct 23, 2017
Zachary Charles, Dimitris Papailiopoulos

* 27 pages, 5 figures 

  Access Model/Code and Paper
CYCLADES: Conflict-free Asynchronous Machine Learning

May 31, 2016
Xinghao Pan, Maximilian Lam, Stephen Tu, Dimitris Papailiopoulos, Ce Zhang, Michael I. Jordan, Kannan Ramchandran, Chris Re, Benjamin Recht


  Access Model/Code and Paper
Perturbed Iterate Analysis for Asynchronous Stochastic Optimization

Mar 25, 2016
Horia Mania, Xinghao Pan, Dimitris Papailiopoulos, Benjamin Recht, Kannan Ramchandran, Michael I. Jordan

* 30 pages 

  Access Model/Code and Paper
Bipartite Correlation Clustering -- Maximizing Agreements

Mar 09, 2016
Megasthenis Asteris, Anastasios Kyrillidis, Dimitris Papailiopoulos, Alexandros G. Dimakis

* To appear in AISTATS 2016 

  Access Model/Code and Paper
Sparse PCA via Bipartite Matchings

Aug 04, 2015
Megasthenis Asteris, Dimitris Papailiopoulos, Anastasios Kyrillidis, Alexandros G. Dimakis


  Access Model/Code and Paper
On the Worst-Case Approximability of Sparse PCA

Jul 21, 2015
Siu On Chan, Dimitris Papailiopoulos, Aviad Rubinstein

* 20 pages 

  Access Model/Code and Paper
Parallel Correlation Clustering on Big Graphs

Jul 20, 2015
Xinghao Pan, Dimitris Papailiopoulos, Samet Oymak, Benjamin Recht, Kannan Ramchandran, Michael I. Jordan


  Access Model/Code and Paper
Provable Deterministic Leverage Score Sampling

Jun 03, 2014
Dimitris Papailiopoulos, Anastasios Kyrillidis, Christos Boutsidis

* 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 

  Access Model/Code and Paper