Christopher De Sa

ORCID

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 139

Top Venues

Publications

Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers. Trans. Mach. Learn. Res. 2024 (2024)
Megan Flynn, Alexander Wang, Dean Edward Alvarez, Christopher De Sa, Anil Damle
STAT: Shrinking Transformers After Training. CoRR (2024)
Wentao Guo, Jikai Long, Yimeng Zeng, Zirui Liu, Xinyu Yang, Yide Ran, Jacob R. Gardner, Osbert Bastani, Christopher De Sa, Xiaodong Yu, Beidi Chen, Zhaozhuo Xu
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity. CoRR (2024)
A. Feder Cooper, Katherine Lee, Madiha Zahrah Choksi, Solon Barocas, Christopher De Sa, James Grimmelmann, Jon M. Kleinberg, Siddhartha Sen, Baobao Zhang
Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification. AAAI (2024)
Si Yi Meng, Antonio Orvieto, Daniel Yiming Cao, Christopher De Sa
Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes. CoRR (2024)
Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, Christopher De Sa
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks. CoRR (2024)
Tao Yu, Toni J. B. Liu, Albert Tseng, Christopher De Sa
Shadow Cones: A Generalized Framework for Partial Order Embeddings. ICLR (2024)
Albert Tseng, Qingyao Sun, David Hou, Christopher De Sa
QTIP: Quantization with Trellises and Incoherence Processing. CoRR (2024)
Tao Yu, Toni J. B. Liu, Albert Tseng, Christopher De Sa
Shadow Cones: Unveiling Partial Orders in Hyperbolic Space. CoRR (2023)
Yucheng Lu, Christopher De Sa
Decentralized Learning: Theoretical Optimality and Practical Improvements. J. Mach. Learn. Res. 24 (2023)
Jue Wang, Yucheng Lu, Binhang Yuan, Beidi Chen, Percy Liang, Christopher De Sa, Christopher Ré, Ce Zhang
CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks. ICML (2023)
Yucheng Lu, Shivani Agrawal, Suvinay Subramanian, Oleg Rybakov, Christopher De Sa, Amir Yazdanbakhsh
STEP: Learning N: M Structured Sparsity Masks from Scratch with Precondition. ICML (2023)
Tao Yu, Christopher De Sa
Random Laplacian Features for Learning with Hyperbolic Space. ICLR (2023)
Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa
QuIP: 2-Bit Quantization of Large Language Models With Guarantees. CoRR (2023)
Yucheng Lu, Shivani Agrawal, Suvinay Subramanian, Oleg Rybakov, Christopher De Sa, Amir Yazdanbakhsh
STEP: Learning N: M Structured Sparsity Masks from Scratch with Precondition. CoRR (2023)
Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré
TART: A plug-and-play Transformer module for task-agnostic reasoning. CoRR (2023)
Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan, Fei Wang, Christopher De Sa, Volodymyr Kuleshov
InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models. ICML (2023)
Wentao Guo, Khiem Pham, Yucheng Lu, Tiancheng Yuan, Charlie F. Ruan, Christopher De Sa
Scale up with Order: Finding Good Data Permutations for Distributed Training. CoRR (2023)
Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov
ModuLoRA: Finetuning 3-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers. CoRR (2023)
Isay Katsman, Eric Ming Chen, Sidhanth Holalkere, Anna Asch, Aaron Lou, Ser-Nam Lim, Christopher De Sa
Riemannian Residual Neural Networks. CoRR (2023)
Yucheng Lu, Conglong Li, Minjia Zhang, Christopher De Sa, Yuxiong He
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam. ICLR (2023)
Oliver E. Richardson, Joseph Y. Halpern, Christopher De Sa
Inference for Probabilistic Dependency Graphs. CoRR (2023)
Zilu Li, Guandao Yang, Xi Deng, Christopher De Sa, Bharath Hariharan, Steve Marschner
Neural Caches for Monte Carlo Partial Differential Equation Solvers. SIGGRAPH Asia (2023)
Isay Katsman, Eric Chen, Sidhanth Holalkere, Anna Asch, Aaron Lou, Ser Nam Lim, Christopher De Sa
Riemannian Residual Neural Networks. NeurIPS (2023)
Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan, Fei Wang, Christopher De Sa, Volodymyr Kuleshov
InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models. CoRR (2023)
Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré
TART: A plug-and-play Transformer module for task-agnostic reasoning. NeurIPS (2023)
A. Feder Cooper, Solon Barocas, Christopher De Sa, Siddhartha Sen
Variance, Self-Consistency, and Arbitrariness in Fair Classification. CoRR (2023)
Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa
QuIP: 2-Bit Quantization of Large Language Models With Guarantees. NeurIPS (2023)
Oliver E. Richardson, Joseph Y. Halpern, Christopher De Sa
Inference for probabilistic dependency graphs. UAI (2023)
Albert Tseng, Tao Yu, Toni J. B. Liu, Christopher De Sa
Coneheads: Hierarchy Aware Attention. NeurIPS (2023)
Albert Tseng, Tao Yu, Toni J. B. Liu, Christopher De Sa
Coneheads: Hierarchy Aware Attention. CoRR (2023)
A. Feder Cooper, Katherine Lee, James Grimmelmann, Daphne Ippolito, Christopher Callison-Burch, Christopher A. Choquette-Choo, Niloofar Mireshghallah, Miles Brundage, David Mimno, Madiha Zahrah Choksi, Jack M. Balkin, Nicholas Carlini, Christopher De Sa, Jonathan Frankle, Deep Ganguli, Bryant Gipson, Andres Guadamuz, Swee Leng Harris, Abigail Z. Jacobs, Elizabeth Joh, Gautam Kamath, Mark Lemley, Cass Matthews, Christine McLeavey, Corynne McSherry, Milad Nasr, Paul Ohm, Adam Roberts, Tom Rubin, Pamela Samuelson, Ludwig Schubert, Kristen Vaccaro, Luis Villa, Felix Wu, Elana Zeide
Report of the 1st Workshop on Generative AI and Law. CoRR (2023)
A. Feder Cooper, Wentao Guo, Khiem Pham, Tiancheng Yuan, Charlie Ruan, Yucheng Lu, Christopher De Sa
CD-GraB: Coordinating Distributed Example Orders for Provably Accelerated Training. NeurIPS (2023)
A. Feder Cooper, Jonathan Frankle, Christopher De Sa
Non-Determinism and the Lawlessness of ML Code. CoRR (2022)
A. Feder Cooper, Jonathan Frankle, Christopher De Sa
Non-Determinism and the Lawlessness of Machine Learning Code. CSLAW (2022)
Jerry Chee, Megan Flynn, Anil Damle, Christopher De Sa
Model Preserving Compression for Neural Networks. NeurIPS (2022)
Ruqi Zhang, Andrew Gordon Wilson, Christopher De Sa
Low-Precision Stochastic Gradient Langevin Dynamics. ICML (2022)
Yucheng Lu, Conglong Li, Minjia Zhang, Christopher De Sa, Yuxiong He
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam. CoRR (2022)
Chengrun Yang, Ziyang Wu, Jerry Chee, Christopher De Sa, Madeleine Udell
How Low Can We Go: Trading Memory for Error in Low-Precision Training. ICLR (2022)
Tao Yu, Christopher De Sa
HyLa: Hyperbolic Laplacian Features For Graph Learning. CoRR (2022)
Yucheng Lu, Si Yi Meng, Christopher De Sa
A General Analysis of Example-Selection for Stochastic Gradient Descent. ICLR (2022)
Yucheng Lu, Wentao Guo, Christopher De Sa
GraB: Finding Provably Better Data Permutations than Random Reshuffling. NeurIPS (2022)
Tao Yu, Yichi Zhang, Zhiru Zhang, Christopher De Sa
Understanding Hyperdimensional Computing for Parallel Single-Pass Learning. CoRR (2022)
Yucheng Lu, Wentao Guo, Christopher De Sa
GraB: Finding Provably Better Data Permutations than Random Reshuffling. CoRR (2022)
Christopher De Sa, Satyen Kale, Jason D. Lee, Ayush Sekhari, Karthik Sridharan
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. NeurIPS (2022)
Ruqi Zhang, Andrew Gordon Wilson, Christopher De Sa
Low-Precision Stochastic Gradient Langevin Dynamics. CoRR (2022)
Tao Yu, Yichi Zhang, Zhiru Zhang, Christopher De Sa
Understanding Hyperdimensional Computing for Parallel Single-Pass Learning. NeurIPS (2022)
Tao Yu, Went Guo, Jianan Canal Li, Tiancheng Yuan, Christopher De Sa
MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point. CoRR (2022)
Yaohui Cai, Weizhe Hua, Hongzheng Chen, G. Edward Suh, Christopher De Sa, Zhiru Zhang
Structured Pruning is All You Need for Pruning CNNs at Initialization. CoRR (2022)
Chengrun Yang, Ziyang Wu, Jerry Chee, Christopher De Sa, Madeleine Udell
How Low Can We Go: Trading Memory for Error in Low-Precision Training. CoRR (2021)
Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean Foster
Variance Reduced Training with Stratified Sampling for Forecasting Models. ICML (2021)
Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean Foster
Variance Reduction in Training Forecasting Models with Subgroup Sampling. CoRR (2021)
Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
Equivariant Manifold Flows. CoRR (2021)
Yucheng Lu, Christopher De Sa
Optimal Complexity in Decentralized Training. ICML (2021)
A. Feder Cooper, Karen Levy, Christopher De Sa
Accuracy-Efficiency Trade-Offs and Accountability in Distributed ML Systems. EAAMO (2021)
Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang
Meta-Learning Divergences for Variational Inference. AISTATS (2021)
A. Feder Cooper, Maria Antoniak, Christopher De Sa, Marilyn Migiel, David Mimno
Tecnologica cosa: Modeling Storyteller Personalities in Boccaccio's Decameron. CoRR (2021)
Johan Björck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision. ICML (2021)
A. Feder Cooper, Yucheng Lu, Christopher De Sa
Hyperparameter Optimization Is Deceiving Us, and How to Stop It. CoRR (2021)
Tao Yu, Christopher De Sa
Representing Hyperbolic Space Accurately using Multi-Component Floats. NeurIPS (2021)
A. Feder Cooper, Yucheng Lu, Jessica Forde, Christopher De Sa
Hyperparameter Optimization Is Deceiving Us, and How to Stop It. NeurIPS (2021)
Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
Equivariant Manifold Flows. NeurIPS (2021)
Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa
PipeMare: Asynchronous Pipeline Parallel DNN Training. MLSys (2021)
Johan Bjorck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger
Low-Precision Reinforcement Learning. CoRR (2021)
Ruqi Zhang, A. Feder Cooper, Christopher De Sa
Asymptotically Optimal Exact Minibatch Metropolis-Hastings. CoRR (2020)
Yucheng Lu, Zheng Li, Christopher De Sa
Towards Optimal Convergence Rate in Decentralized Stochastic Training. CoRR (2020)
Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
Neural Manifold Ordinary Differential Equations. CoRR (2020)
Yucheng Lu, Christopher De Sa
Moniqua: Modulo Quantized Communication in Decentralized SGD. ICML (2020)
Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang
Meta-Learning for Variational Inference. CoRR (2020)
Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge J. Belongie, Ser-Nam Lim, Christopher De Sa
Differentiating through the Fréchet Mean. ICML (2020)
Zhijing Li, Christopher De Sa, Adrian Sampson
Optimizing JPEG Quantization for Classification Networks. CoRR (2020)
Ruqi Zhang, A. Feder Cooper, Christopher De Sa
Asymptotically Optimal Exact Minibatch Metropolis-Hastings. NeurIPS (2020)
Pedram Zamirai, Jian Zhang, Christopher R. Aberger, Christopher De Sa
Revisiting BFloat16 Training. CoRR (2020)
Ruqi Zhang, A. Feder Cooper, Christopher De Sa
AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC. CoRR (2020)
Yucheng Lu, Christopher De Sa
Moniqua: Modulo Quantized Communication in Decentralized SGD. CoRR (2020)
Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
Neural Manifold Ordinary Differential Equations. NeurIPS (2020)
Christopher De Sa
Random Reshuffling is Not Always Better. NeurIPS (2020)
Yucheng Lu, Jack Nash, Christopher De Sa
MixML: A Unified Analysis of Weakly Consistent Parallel Learning. CoRR (2020)
A. Feder Cooper, Karen Levy, Christopher De Sa
Regulating Accuracy-Efficiency Trade-Offs in Distributed Machine Learning Systems. CoRR (2020)
Ruqi Zhang, A. Feder Cooper, Christopher De Sa
AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC. AISTATS (2020)
Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge J. Belongie, Ser-Nam Lim, Christopher De Sa
Differentiating through the Fréchet Mean. CoRR (2020)
Ruqi Zhang, Christopher De Sa
Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees. CoRR (2019)
Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa
QPyTorch: A Low-Precision Arithmetic Simulation Framework. CoRR (2019)
Tao Yu, Christopher De Sa
Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models. NeurIPS (2019)
Zheng Li, Christopher De Sa
Dimension-Free Bounds for Low-Precision Training. NeurIPS (2019)
Ken Birman, Bharath Hariharan, Christopher De Sa
Cloud-Hosted Intelligence for Real-time IoT Applications. ACM SIGOPS Oper. Syst. Rev. 53 (1) (2019)
Weizhe Hua, Yuan Zhou, Christopher De Sa, Zhiru Zhang, G. Edward Suh
Channel Gating Neural Networks. NeurIPS (2019)
Ruqi Zhang, Christopher De Sa
Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees. NeurIPS (2019)
Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
Building Efficient Deep Neural Networks With Unitary Group Convolutions. CVPR (2019)
Christopher De Sa, Ihab F. Ilyas, Benny Kimelfeld, Christopher Ré, Theodoros Rekatsinas
A Formal Framework for Probabilistic Unclean Databases. ICDT (2019)
Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting. CoRR (2019)
Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa
SWALP : Stochastic Weight Averaging in Low Precision Training. ICML (2019)
Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
Improving Neural Network Quantization without Retraining using Outlier Channel Splitting. ICML (2019)
Ritchie Zhao, Christopher De Sa, Zhiru Zhang
Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelerators. CoRR (2019)
Jayadev Acharya, Christopher De Sa, Dylan J. Foster, Karthik Sridharan
Distributed Learning with Sublinear Communication. CoRR (2019)
Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa
PipeMare: Asynchronous Pipeline Parallel DNN Training. CoRR (2019)
Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Eric Chung, Bill Dally, Jeff Dean, Inderjit S. Dhillon, Alexandros G. 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 M. Hazelwood, Furong Huang, Martin Jaggi, Kevin G. Jamieson, Michael I. Jordan, Gauri Joshi, Rania Khalaf, Jason Knight, Jakub Konecný, Tim Kraska, Arun Kumar, Anastasios Kyrillidis, Jing Li, Samuel Madden, H. Brendan McMahan, Erik Meijer, Ioannis Mitliagkas, Rajat Monga, Derek Gordon Murray, Dimitris S. Papailiopoulos, Gennady Pekhimenko, Theodoros Rekatsinas, Afshin Rostamizadeh, Christopher Ré, Christopher De Sa, Hanie Sedghi, Siddhartha Sen, Virginia Smith, Alex Smola, Dawn Song, Evan R. Sparks, Ion Stoica, Vivienne Sze, Madeleine Udell, Joaquin Vanschoren, Shivaram Venkataraman, Rashmi Vinayak, Markus Weimer, Andrew Gordon Wilson, Eric P. Xing, Matei Zaharia, Ce Zhang, Ameet Talwalkar
SysML: The New Frontier of Machine Learning Systems. CoRR (2019)
Weizhe Hua, Yuan Zhou, Christopher De Sa, Zhiru Zhang, G. Edward Suh
Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating. MICRO (2019)
Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa
SWALP : Stochastic Weight Averaging in Low-Precision Training. CoRR (2019)
Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa
QPyTorch: A Low-Precision Arithmetic Simulation Framework. EMC2@NeurIPS (2019)

Christopher De Sa.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Christopher De Sa