Christopher De Sa

155 papers A* 54A 6Journal 84Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Estimating near-verbatim extraction risk in language models with decoding-constrained beam search. CoRR A. Feder Cooper, Mark A. Lemley, Christopher De Sa, Lea Duesterwald, Allison Casasola, Jamie Hayes, Katherine Lee, Daniel E. Ho, Percy Liang
2026	J	`jnl`	L CoRR Albert Tseng, Christopher De Sa
2025	J	`jnl`	Compute-Optimal LLMs Provably Generalize Better With Scale. CoRR Marc Finzi, Sanyam Kapoor, Diego Granziol, Anming Gu, Christopher De Sa, J. Zico Kolter, Andrew Gordon Wilson
2025	A*	`conf`	Compute-Optimal LLMs Provably Generalize Better with Scale. ICLR Marc Anton Finzi, Sanyam Kapoor, Diego Granziol, Anming Gu, Christopher De Sa, J. Zico Kolter, Andrew Gordon Wilson
2025	J	`jnl`	Extracting memorized pieces of (copyrighted) books from open-weight language models. CoRR A. Feder Cooper, Aaron Gokaslan, Amy Cyphert, Christopher De Sa, Mark A. Lemley, Daniel E. Ho, Percy Liang
2025	J	`jnl`	Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere? CoRR Si Yi Meng, Baptiste Goujaud, Antonio Orvieto, Christopher De Sa
2025	J	`jnl`	Model-Preserving Adaptive Rounding. CoRR Albert Tseng, Zhaofeng Sun, Christopher De Sa
2025	A*	`conf`	Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity. ICLR 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
2024	A*	`conf`	Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification. AAAI A. Feder Cooper, Katherine Lee, Madiha Zahrah Choksi, Solon Barocas, Christopher De Sa, James Grimmelmann, Jon M. Kleinberg, Siddhartha Sen, Baobao Zhang
2024	A*	`conf`	Diffusion Models With Learned Adaptive Noise. NeurIPS Subham S. Sahoo, Aaron Gokaslan, Christopher De Sa, Volodymyr Kuleshov
2024	J	`jnl`	Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes. CoRR Si Yi Meng, Antonio Orvieto, Daniel Yiming Cao, Christopher De Sa
2024	J	`jnl`	Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice. CoRR A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski, Katja Filippova, Ken Ziyu Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Niloofar Mireshghallah, Ilia Shumailov, Eleni Triantafillou, Peter Kairouz, Nicole Mitchell, Percy Liang, Daniel E. Ho, Yejin Choi, Sanmi Koyejo, Fernando A. Delgado, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Solon Barocas, Amy Cyphert, Mark A. Lemley, danah boyd, Jennifer Wortman Vaughan, Miles Brundage, David Bau, Seth Neel, Abigail Z. Jacobs, Andreas Terzis, Hanna M. Wallach, Nicolas Papernot, Katherine Lee
2024	J	`jnl`	ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers. Trans. Mach. Learn. Res. Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov
2024	—	`ed.`	Proceedings of the Seventh Annual Conference on Machine Learning and Systems, MLSys 2024, Santa Clara, CA, USA, May 13-16, 2024 MLSys Phillip B. Gibbons, Gennady Pekhimenko, Christopher De Sa
2024	A*	`conf`	QTIP: Quantization with Trellises and Incoherence Processing. NeurIPS Albert Tseng, Qingyao Sun, David Hou, Christopher De Sa
2024	J	`jnl`	QTIP: Quantization with Trellises and Incoherence Processing. CoRR Albert Tseng, Qingyao Sun, David Hou, Christopher De Sa
2024	A*	`conf`	QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks. ICML Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, Christopher De Sa
2024	J	`jnl`	QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks. CoRR Albert Tseng, Jerry Chee, Qingyao Sun, Volodymyr Kuleshov, Christopher De Sa
2024	J	`jnl`	STAT: Shrinking Transformers After Training. CoRR Megan Flynn, Alexander Wang, Dean Edward Alvarez, Christopher De Sa, Anil Damle
2024	A*	`conf`	Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices. NeurIPS Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Charlie Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson
2024	J	`jnl`	Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices. CoRR Andres Potapczynski, Shikai Qiu, Marc Finzi, Christopher Ferri, Zixi Chen, Micah Goldblum, C. Bayan Bruss, Christopher De Sa, Andrew Gordon Wilson
2024	A*	`conf`	Shadow Cones: A Generalized Framework for Partial Order Embeddings. ICLR Tao Yu, Toni J. B. Liu, Albert Tseng, Christopher De Sa
2024	J	`jnl`	Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity. CoRR 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
2023	A*	`conf`	CD-GraB: Coordinating Distributed Example Orders for Provably Accelerated Training. NeurIPS A. Feder Cooper, Wentao Guo, Khiem Pham, Tiancheng Yuan, Charlie Ruan, Yucheng Lu, Christopher De Sa
2023	A*	`conf`	CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks. ICML Jue Wang, Yucheng Lu, Binhang Yuan, Beidi Chen, Percy Liang, Christopher De Sa, Christopher Ré, Ce Zhang
2023	A*	`conf`	Coneheads: Hierarchy Aware Attention. NeurIPS Albert Tseng, Tao Yu, Toni J. B. Liu, Christopher De Sa
2023	J	`jnl`	Coneheads: Hierarchy Aware Attention. CoRR Albert Tseng, Tao Yu, Toni J. B. Liu, Christopher De Sa
2023	J	`jnl`	Decentralized Learning: Theoretical Optimality and Practical Improvements. J. Mach. Learn. Res. Yucheng Lu, Christopher De Sa
2023	J	`jnl`	Inference for Probabilistic Dependency Graphs. CoRR Oliver E. Richardson, Joseph Y. Halpern, Christopher De Sa
2023	A	`conf`	Inference for probabilistic dependency graphs. UAI Oliver E. Richardson, Joseph Y. Halpern, Christopher De Sa
2023	A*	`conf`	InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models. ICML Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan, Fei Wang, Christopher De Sa, Volodymyr Kuleshov
2023	J	`jnl`	InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models. CoRR Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan, Fei Wang, Christopher De Sa, Volodymyr Kuleshov
2023	A*	`conf`	Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam. ICLR Yucheng Lu, Conglong Li, Minjia Zhang, Christopher De Sa, Yuxiong He
2023	J	`jnl`	ModuLoRA: Finetuning 3-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers. CoRR Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov
2023	A*	`conf`	Neural Caches for Monte Carlo Partial Differential Equation Solvers. SIGGRAPH Asia Zilu Li, Guandao Yang, Xi Deng, Christopher De Sa, Bharath Hariharan, Steve Marschner
2023	A*	`conf`	QuIP: 2-Bit Quantization of Large Language Models With Guarantees. NeurIPS Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa
2023	J	`jnl`	QuIP: 2-Bit Quantization of Large Language Models With Guarantees. CoRR Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa
2023	A*	`conf`	Random Laplacian Features for Learning with Hyperbolic Space. ICLR Tao Yu, Christopher De Sa
2023	J	`jnl`	Report of the 1st Workshop on Generative AI and Law. CoRR 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 A. 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
2023	A*	`conf`	Riemannian Residual Neural Networks. NeurIPS Isay Katsman, Eric Ming Chen, Sidhanth Holalkere, Anna Asch, Aaron Lou, Ser Nam Lim, Christopher De Sa
2023	J	`jnl`	Riemannian Residual Neural Networks. CoRR Isay Katsman, Eric Ming Chen, Sidhanth Holalkere, Anna Asch, Aaron Lou, Ser-Nam Lim, Christopher De Sa
2023	A*	`conf`	STEP: Learning N: M Structured Sparsity Masks from Scratch with Precondition. ICML Yucheng Lu, Shivani Agrawal, Suvinay Subramanian, Oleg Rybakov, Christopher De Sa, Amir Yazdanbakhsh
2023	J	`jnl`	STEP: Learning N: M Structured Sparsity Masks from Scratch with Precondition. CoRR Yucheng Lu, Shivani Agrawal, Suvinay Subramanian, Oleg Rybakov, Christopher De Sa, Amir Yazdanbakhsh
2023	J	`jnl`	Scale up with Order: Finding Good Data Permutations for Distributed Training. CoRR Wentao Guo, Khiem Pham, Yucheng Lu, Tiancheng Yuan, Charlie F. Ruan, Christopher De Sa
2023	J	`jnl`	Shadow Cones: Unveiling Partial Orders in Hyperbolic Space. CoRR Tao Yu, Toni J. B. Liu, Albert Tseng, Christopher De Sa
2023	A*	`conf`	TART: A plug-and-play Transformer module for task-agnostic reasoning. NeurIPS Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré
2023	J	`jnl`	TART: A plug-and-play Transformer module for task-agnostic reasoning. CoRR Kush Bhatia, Avanika Narayan, Christopher De Sa, Christopher Ré
2023	J	`jnl`	Variance, Self-Consistency, and Arbitrariness in Fair Classification. CoRR A. Feder Cooper, Solon Barocas, Christopher De Sa, Siddhartha Sen
2022	A*	`conf`	A General Analysis of Example-Selection for Stochastic Gradient Descent. ICLR Yucheng Lu, Si Yi Meng, Christopher De Sa
2022	A*	`conf`	From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. NeurIPS Christopher De Sa, Satyen Kale, Jason D. Lee, Ayush Sekhari, Karthik Sridharan
2022	A*	`conf`	GraB: Finding Provably Better Data Permutations than Random Reshuffling. NeurIPS Yucheng Lu, Wentao Guo, Christopher De Sa
2022	J	`jnl`	GraB: Finding Provably Better Data Permutations than Random Reshuffling. CoRR Yucheng Lu, Wentao Guo, Christopher De Sa
2022	A*	`conf`	How Low Can We Go: Trading Memory for Error in Low-Precision Training. ICLR Chengrun Yang, Ziyang Wu, Jerry Chee, Christopher De Sa, Madeleine Udell
2022	J	`jnl`	HyLa: Hyperbolic Laplacian Features For Graph Learning. CoRR Tao Yu, Christopher De Sa
2022	A*	`conf`	Low-Precision Stochastic Gradient Langevin Dynamics. ICML Ruqi Zhang, Andrew Gordon Wilson, Christopher De Sa
2022	J	`jnl`	Low-Precision Stochastic Gradient Langevin Dynamics. CoRR Ruqi Zhang, Andrew Gordon Wilson, Christopher De Sa
2022	J	`jnl`	MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point. CoRR Tao Yu, Went Guo, Jianan Canal Li, Tiancheng Yuan, Christopher De Sa
2022	J	`jnl`	Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam. CoRR Yucheng Lu, Conglong Li, Minjia Zhang, Christopher De Sa, Yuxiong He
2022	A*	`conf`	Model Preserving Compression for Neural Networks. NeurIPS Jerry Chee, Megan Flynn, Anil Damle, Christopher De Sa
2022	J	`jnl`	Non-Determinism and the Lawlessness of ML Code. CoRR A. Feder Cooper, Jonathan Frankle, Christopher De Sa
2022	—	`conf`	Non-Determinism and the Lawlessness of Machine Learning Code. CSLAW A. Feder Cooper, Jonathan Frankle, Christopher De Sa
2022	J	`jnl`	Structured Pruning is All You Need for Pruning CNNs at Initialization. CoRR Yaohui Cai, Weizhe Hua, Hongzheng Chen, G. Edward Suh, Christopher De Sa, Zhiru Zhang
2022	A*	`conf`	Understanding Hyperdimensional Computing for Parallel Single-Pass Learning. NeurIPS Tao Yu, Yichi Zhang, Zhiru Zhang, Christopher De Sa
2022	J	`jnl`	Understanding Hyperdimensional Computing for Parallel Single-Pass Learning. CoRR Tao Yu, Yichi Zhang, Zhiru Zhang, Christopher De Sa
2021	—	`conf`	Accuracy-Efficiency Trade-Offs and Accountability in Distributed ML Systems. EAAMO A. Feder Cooper, Karen Levy, Christopher De Sa
2021	A*	`conf`	Equivariant Manifold Flows. NeurIPS Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
2021	J	`jnl`	Equivariant Manifold Flows. CoRR Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
2021	J	`jnl`	How Low Can We Go: Trading Memory for Error in Low-Precision Training. CoRR Chengrun Yang, Ziyang Wu, Jerry Chee, Christopher De Sa, Madeleine Udell
2021	A*	`conf`	Hyperparameter Optimization Is Deceiving Us, and How to Stop It. NeurIPS A. Feder Cooper, Yucheng Lu, Jessica Forde, Christopher De Sa
2021	J	`jnl`	Hyperparameter Optimization Is Deceiving Us, and How to Stop It. CoRR A. Feder Cooper, Yucheng Lu, Christopher De Sa
2021	J	`jnl`	Low-Precision Reinforcement Learning. CoRR Johan Bjorck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger
2021	A*	`conf`	Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision. ICML Johan Björck, Xiangyu Chen, Christopher De Sa, Carla P. Gomes, Kilian Q. Weinberger
2021	A	`conf`	Meta-Learning Divergences for Variational Inference. AISTATS Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang
2021	A*	`conf`	Optimal Complexity in Decentralized Training. ICML Yucheng Lu, Christopher De Sa
2021	—	`conf`	PipeMare: Asynchronous Pipeline Parallel DNN Training. MLSys Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa
2021	A*	`conf`	Representing Hyperbolic Space Accurately using Multi-Component Floats. NeurIPS Tao Yu, Christopher De Sa
2021	J	`jnl`	Tecnologica cosa: Modeling Storyteller Personalities in Boccaccio's Decameron. CoRR A. Feder Cooper, Maria Antoniak, Christopher De Sa, Marilyn Migiel, David Mimno
2021	A*	`conf`	Variance Reduced Training with Stratified Sampling for Forecasting Models. ICML Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean P. Foster
2021	J	`jnl`	Variance Reduction in Training Forecasting Models with Subgroup Sampling. CoRR Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean P. Foster
2020	A	`conf`	AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC. AISTATS Ruqi Zhang, A. Feder Cooper, Christopher De Sa
2020	J	`jnl`	AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC. CoRR Ruqi Zhang, A. Feder Cooper, Christopher De Sa
2020	A*	`conf`	Asymptotically Optimal Exact Minibatch Metropolis-Hastings. NeurIPS Ruqi Zhang, A. Feder Cooper, Christopher De Sa
2020	J	`jnl`	Asymptotically Optimal Exact Minibatch Metropolis-Hastings. CoRR Ruqi Zhang, A. Feder Cooper, Christopher De Sa
2020	A*	`conf`	Differentiating through the Fréchet Mean. ICML Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge J. Belongie, Ser-Nam Lim, Christopher De Sa
2020	J	`jnl`	Differentiating through the Fréchet Mean. CoRR Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge J. Belongie, Ser-Nam Lim, Christopher De Sa
2020	J	`jnl`	Meta-Learning for Variational Inference. CoRR Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang
2020	J	`jnl`	MixML: A Unified Analysis of Weakly Consistent Parallel Learning. CoRR Yucheng Lu, Jack Nash, Christopher De Sa
2020	A*	`conf`	Moniqua: Modulo Quantized Communication in Decentralized SGD. ICML Yucheng Lu, Christopher De Sa
2020	J	`jnl`	Moniqua: Modulo Quantized Communication in Decentralized SGD. CoRR Yucheng Lu, Christopher De Sa
2020	A*	`conf`	Neural Manifold Ordinary Differential Equations. NeurIPS Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
2020	J	`jnl`	Neural Manifold Ordinary Differential Equations. CoRR Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
2020	J	`jnl`	Optimizing JPEG Quantization for Classification Networks. CoRR Zhijing Li, Christopher De Sa, Adrian Sampson
2020	A*	`conf`	Random Reshuffling is Not Always Better. NeurIPS Christopher De Sa
2020	J	`jnl`	Regulating Accuracy-Efficiency Trade-Offs in Distributed Machine Learning Systems. CoRR A. Feder Cooper, Karen Levy, Christopher De Sa
2020	J	`jnl`	Revisiting BFloat16 Training. CoRR Pedram Zamirai, Jian Zhang, Christopher R. Aberger, Christopher De Sa
2020	J	`jnl`	Towards Optimal Convergence Rate in Decentralized Stochastic Training. CoRR Yucheng Lu, Zheng Li, Christopher De Sa
2019	A	`conf`	A Formal Framework for Probabilistic Unclean Databases. ICDT Christopher De Sa, Ihab F. Ilyas, Benny Kimelfeld, Christopher Ré, Theodoros Rekatsinas
2019	A*	`conf`	Boosting the Performance of CNN Accelerators with Dynamic Fine-Grained Channel Gating. MICRO Weizhe Hua, Yuan Zhou, Christopher De Sa, Zhiru Zhang, G. Edward Suh
2019	A*	`conf`	Building Efficient Deep Neural Networks With Unitary Group Convolutions. CVPR Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
2019	A*	`conf`	Channel Gating Neural Networks. NeurIPS Weizhe Hua, Yuan Zhou, Christopher De Sa, Zhiru Zhang, G. Edward Suh
2019	J	`jnl`	Cloud-Hosted Intelligence for Real-time IoT Applications. ACM SIGOPS Oper. Syst. Rev. Ken Birman, Bharath Hariharan, Christopher De Sa
2019	A*	`conf`	Dimension-Free Bounds for Low-Precision Training. NeurIPS Zheng Li, Christopher De Sa
2019	J	`jnl`	Distributed Learning with Sublinear Communication. CoRR Jayadev Acharya, Christopher De Sa, Dylan J. Foster, Karthik Sridharan
2019	A*	`conf`	Improving Neural Network Quantization without Retraining using Outlier Channel Splitting. ICML Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
2019	J	`jnl`	Improving Neural Network Quantization without Retraining using Outlier Channel Splitting. CoRR Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
2019	A*	`conf`	Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models. NeurIPS Tao Yu, Christopher De Sa
2019	J	`jnl`	Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelerators. CoRR Ritchie Zhao, Christopher De Sa, Zhiru Zhang
2019	J	`jnl`	PipeMare: Asynchronous Pipeline Parallel DNN Training. CoRR Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher R. Aberger, Christopher De Sa
2019	A*	`conf`	Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees. NeurIPS Ruqi Zhang, Christopher De Sa
2019	J	`jnl`	Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees. CoRR Ruqi Zhang, Christopher De Sa
2019	—	`conf`	QPyTorch: A Low-Precision Arithmetic Simulation Framework. EMC2@NeurIPS Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa
2019	J	`jnl`	QPyTorch: A Low-Precision Arithmetic Simulation Framework. CoRR Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa
2019	A*	`conf`	SWALP : Stochastic Weight Averaging in Low Precision Training. ICML Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa
2019	J	`jnl`	SWALP : Stochastic Weight Averaging in Low-Precision Training. CoRR Guandao Yang, Tianyi Zhang, Polina Kirichenko, Junwen Bai, Andrew Gordon Wilson, Christopher De Sa
2019	J	`jnl`	SysML: The New Frontier of Machine Learning Systems. CoRR Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen, Peter Bailis, Sarah Bird, Nicholas Carlini, Bryan Catanzaro, Eric S. 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 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 Randall 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
2018	J	`jnl`	A Formal Framework For Probabilistic Unclean Databases. CoRR Christopher De Sa, Ihab F. Ilyas, Benny Kimelfeld, Christopher Ré, Theodoros Rekatsinas
2018	J	`jnl`	A Kernel Theory of Modern Data Augmentation. CoRR Tri Dao, Albert Gu, Alexander J. Ratner, Virginia Smith, Christopher De Sa, Christopher Ré
2018	A*	`conf`	A Two-pronged Progress in Structured Dense Matrix Vector Multiplication. SODA Christopher De Sa, Albert Gu, Rohan Puttagunta, Christopher Ré, Atri Rudra
2018	A	`conf`	Accelerated Stochastic Power Iteration. AISTATS Peng Xu, Bryan D. He, Christopher De Sa, Ioannis Mitliagkas, Christopher Ré
2018	J	`jnl`	Building Efficient Deep Neural Networks with Unitary Group Convolutions. CoRR Ritchie Zhao, Yuwei Hu, Jordan Dotzel, Christopher De Sa, Zhiru Zhang
2018	J	`jnl`	Channel Gating Neural Networks. CoRR Weizhe Hua, Christopher De Sa, Zhiru Zhang, G. Edward Suh
2018	J	`jnl`	High-Accuracy Low-Precision Training. CoRR Christopher De Sa, Megan Leszczynski, Jian Zhang, Alana Marzoev, Christopher R. Aberger, Kunle Olukotun, Christopher Ré
2018	A*	`conf`	Minibatch Gibbs Sampling on Large Graphical Models. ICML Christopher De Sa, Vincent Chen, Wing Wong
2018	J	`jnl`	Minibatch Gibbs Sampling on Large Graphical Models. CoRR Christopher De Sa, Vincent Chen, Wing Wong
2018	A*	`conf`	Representation Tradeoffs for Hyperbolic Embeddings. ICML Frederic Sala, Christopher De Sa, Albert Gu, Christopher Ré
2018	J	`jnl`	Representation Tradeoffs for Hyperbolic Embeddings. CoRR Christopher De Sa, Albert Gu, Christopher Ré, Frederic Sala
2018	J	`jnl`	Soft optoelectronic sensory foams with proprioception. Sci. Robotics Christopher De Sa, Robert F. Shepherd
2018	A*	`conf`	The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory. PODC Dan Alistarh, Christopher De Sa, Nikola Konstantinov
2018	J	`jnl`	The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory. CoRR Dan Alistarh, Christopher De Sa, Nikola Konstantinov
2017	J	`jnl`	Accelerated Stochastic Power Iteration. CoRR Christopher De Sa, Bryan D. He, Ioannis Mitliagkas, Christopher Ré, Peng Xu
2017	A*	`conf`	Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling. IJCAI Christopher De Sa, Kunle Olukotun, Christopher Ré
2017	—	`conf`	Flipper: A Systematic Approach to Debugging Training Sets. HILDA@SIGMOD Paroma Varma, Dan Iter, Christopher De Sa, Christopher Ré
2017	—	`conf`	Gaussian Quadrature for Kernel Features. NIPS Tri Dao, Christopher De Sa, Christopher Ré
2017	J	`jnl`	Gaussian Quadrature for Kernel Features. CoRR Tri Dao, Christopher De Sa, Christopher Ré
2017	J	`jnl`	Incremental knowledge base construction using DeepDive. VLDB J. Christopher De Sa, Alexander Ratner, Christopher Ré, Jaeho Shin, Feiran Wang, Sen Wu, Ce Zhang
2017	A*	`conf`	Understanding and Optimizing Asynchronous Low-Precision Stochastic Gradient Descent. ISCA Christopher De Sa, Matthew Feldman, Christopher Ré, Kunle Olukotun
2016	—	`conf`	Data Programming: Creating Large Training Sets, Quickly. NIPS Alexander J. Ratner, Christopher De Sa, Sen Wu, Daniel Selsam, Christopher Ré
2016	J	`jnl`	Data Programming: Creating Large Training Sets, Quickly. CoRR Alexander Ratner, Christopher De Sa, Sen Wu, Daniel Selsam, Christopher Ré
2016	J	`jnl`	DeepDive: Declarative Knowledge Base Construction. SIGMOD Rec. Christopher De Sa, Alexander Ratner, Christopher Ré, Jaeho Shin, Feiran Wang, Sen Wu, Ce Zhang
2016	A*	`conf`	Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling. ICML Christopher De Sa, Christopher Ré, Kunle Olukotun
2016	J	`jnl`	Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling. CoRR Christopher De Sa, Kunle Olukotun, Christopher Ré
2016	A*	`conf`	Generating Configurable Hardware from Parallel Patterns. ASPLOS Raghu Prabhakar, David Koeplinger, Kevin J. Brown, HyoukJoong Lee, Christopher De Sa, Christos Kozyrakis, Kunle Olukotun
2016	A	`conf`	Have abstraction and eat performance, too: optimized heterogeneous computing with parallel patterns. CGO Kevin J. Brown, HyoukJoong Lee, Tiark Rompf, Arvind K. Sujeeth, Christopher De Sa, Christopher R. Aberger, Kunle Olukotun
2016	J	`jnl`	Parallel SGD: When does averaging help? CoRR Jian Zhang, Christopher De Sa, Ioannis Mitliagkas, Christopher Ré
2016	—	`conf`	Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much. NIPS Bryan D. He, Christopher De Sa, Ioannis Mitliagkas, Christopher Ré
2016	J	`jnl`	Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much. CoRR Bryan D. He, Christopher De Sa, Ioannis Mitliagkas, Christopher Ré
2016	J	`jnl`	Socratic Learning. CoRR Rose Yu, Paroma Varma, Dan Iter, Christopher De Sa, Christopher Ré
2015	J	`jnl`	Generating Configurable Hardware from Parallel Patterns. CoRR Raghu Prabhakar, David Koeplinger, Kevin J. Brown, HyoukJoong Lee, Christopher De Sa, Christos Kozyrakis, Kunle Olukotun
2015	A*	`conf`	Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems. ICML Christopher De Sa, Christopher Ré, Kunle Olukotun
2015	J	`jnl`	Incremental Knowledge Base Construction Using DeepDive. Proc. VLDB Endow. Jaeho Shin, Sen Wu, Feiran Wang, Christopher De Sa, Ce Zhang, Christopher Ré
2015	—	`conf`	Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width. NIPS Christopher De Sa, Ce Zhang, Kunle Olukotun, Christopher Ré
2015	J	`jnl`	Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width. CoRR Christopher De Sa, Ce Zhang, Kunle Olukotun, Christopher Ré
2015	J	`jnl`	Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms. CoRR Christopher De Sa, Ce Zhang, Kunle Olukotun, Christopher Ré
2015	—	`conf`	Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms. NIPS Christopher De Sa, Ce Zhang, Kunle Olukotun, Christopher Ré
2014	J	`jnl`	Global Convergence of Stochastic Gradient Descent for Some Nonconvex Matrix Problems. CoRR Christopher De Sa, Kunle Olukotun, Christopher Ré