Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Christopher De Sa

Tecnologica cosa: Modeling Storyteller Personalities in Boccaccio's Decameron


Sep 22, 2021
A. Feder Cooper, Maria Antoniak, Christopher De Sa, Marilyn Migiel, David Mimno

* The 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature (co-located with EMNLP 2021) 

  Access Paper or Ask Questions

Equivariant Manifold Flows


Jul 19, 2021
Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa

* Preprint 

  Access Paper or Ask Questions

How Low Can We Go: Trading Memory for Error in Low-Precision Training


Jun 18, 2021
Chengrun Yang, Ziyang Wu, Jerry Chee, Christopher De Sa, Madeleine Udell


  Access Paper or Ask Questions

Variance Reduction in Training Forecasting Models with Subgroup Sampling


Mar 02, 2021
Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean Foster


  Access Paper or Ask Questions

Low-Precision Reinforcement Learning


Feb 26, 2021
Johan Bjorck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger


  Access Paper or Ask Questions

Hyperparameter Optimization Is Deceiving Us, and How to Stop It


Feb 10, 2021
A. Feder Cooper, Yucheng Lu, Christopher De Sa


  Access Paper or Ask Questions

Revisiting BFloat16 Training


Oct 13, 2020
Pedram Zamirai, Jian Zhang, Christopher R. Aberger, Christopher De Sa


  Access Paper or Ask Questions

Regulating Accuracy-Efficiency Trade-Offs in Distributed Machine Learning Systems


Jul 13, 2020
A. Feder Cooper, Karen Levy, Christopher De Sa


  Access Paper or Ask Questions

Meta-Learning for Variational Inference


Jul 06, 2020
Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang


  Access Paper or Ask Questions

Asymptotically Optimal Exact Minibatch Metropolis-Hastings


Jun 23, 2020
Ruqi Zhang, A. Feder Cooper, Christopher De Sa


  Access Paper or Ask Questions

Neural Manifold Ordinary Differential Equations


Jun 18, 2020
Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa

* Submitted to NeurIPS 2020 

  Access Paper or Ask Questions

Towards Optimal Convergence Rate in Decentralized Stochastic Training


Jun 15, 2020
Yucheng Lu, Zheng Li, Christopher De Sa


  Access Paper or Ask Questions

MixML: A Unified Analysis of Weakly Consistent Parallel Learning


Jun 06, 2020
Yucheng Lu, Jack Nash, Christopher De Sa


  Access Paper or Ask Questions

Optimizing JPEG Quantization for Classification Networks


Mar 05, 2020
Zhijing Li, Christopher De Sa, Adrian Sampson

* 6 pages, 13 figures, Resource-Constrained Machine Learning (ReCoML) Workshop of MLSys 2020 Conference, Austin, TX, USA, 2020 

  Access Paper or Ask Questions

Differentiating through the Fréchet Mean


Mar 05, 2020
Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge Belongie, Ser-Nam Lim, Christopher De Sa

* Preprint, 35 pages, 9 figures 

  Access Paper or Ask Questions

AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC


Feb 29, 2020
Ruqi Zhang, A. Feder Cooper, Christopher De Sa

* Published at AISTATS 2020 

  Access Paper or Ask Questions

Moniqua: Modulo Quantized Communication in Decentralized SGD


Feb 26, 2020
Yucheng Lu, Christopher De Sa


  Access Paper or Ask Questions

Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees


Nov 21, 2019
Ruqi Zhang, Christopher De Sa

* Published at NeurIPS 2019 

  Access Paper or Ask Questions

Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelerators


Oct 13, 2019
Ritchie Zhao, Christopher De Sa, Zhiru Zhang

* Preprint, work in progress. 8 pages 

  Access Paper or Ask Questions

PipeMare: Asynchronous Pipeline Parallel DNN Training


Oct 09, 2019
Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa


  Access Paper or Ask Questions

QPyTorch: A Low-Precision Arithmetic Simulation Framework


Oct 09, 2019
Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa

* NeurIPS 2019 EMC^2 Workshop on Energy Efficient Machine Learning and Cognitive Computing 

  Access Paper or Ask Questions

SWALP : Stochastic Weight Averaging in Low-Precision Training


May 20, 2019
Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa

* Published at ICML 2019 

  Access Paper or Ask Questions

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 Paper or Ask Questions

Distributed Learning with Sublinear Communication


Mar 18, 2019
Jayadev Acharya, Christopher De Sa, Dylan J. Foster, Karthik Sridharan


  Access Paper or Ask Questions