← Authors

Christopher De Sa

30 papers · 2015–2025 · 10 conferences · across top CS/AI conferences

Achievements

๐Ÿƒ Academic Marathon (10) ๐Ÿฃ Hot Topic Early Bird ๐ŸŒ‰ Interdisciplinary Bridge ๐Ÿ—บ๏ธ Taxonomy Completionist (13) ๐Ÿงญ Keyword Pioneer ๐Ÿ Cross-Pollinator (13) ๐ŸŒˆ Renaissance Researcher (9) ๐ŸŒ Conference Polyglot (10) ๐Ÿ‘‘ Triple Crown ๐Ÿ† Grand Slam ๐Ÿ† Keyword Champion (2) ๐Ÿ’Ž Century Club (30) โšก Prolific Year (5) ๐Ÿ—ƒ๏ธ Keyword Collector (127) ๐Ÿ”ฅ Unstoppable (11)

Conferences

ICML (12) ICLR (7) AISTATS (3) NIPS (2) AAAI (1) CVPR (1) EMNLP (1) IJCAI (1) JMLR (1) UAI (1)

Top co-authors

Yucheng Lu (8) Christopher Re (3) Kunle Olukotun (3) Albert Tseng (3) Ruqi Zhang (3) Andrew Gordon Wilson (3) Tao Yu (2) Qingyao Sun (2) Volodymyr Kuleshov (2) Jerry Chee (2)

Research topics

Digital Humanities (1)

Keywords

model compression (5) stochastic gradient descent (4) distributed learning (3) non-convex optimization (3) markov chain monte carlo (3) stochastic optimization (3) decentralized learning (2) low-precision training (2) bayesian sampling (2) distributed training (2) variance reduction (2) mixing time (2) gibbs sampling (2) gossip algorithm (2) bias correction (2) iteration complexity (2) representation learning (2) ensemble learning (1) variational inference (1) neural network pruning (1)

Papers

Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity ICLR 2025
Compute-Optimal LLMs Provably Generalize Better with Scale ICLR 2025
Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification AAAI 2024
Shadow Cones: A Generalized Framework for Partial Order Embeddings ICLR 2024
QuIP$#$: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks ICML 2024
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices NIPS 2024
QTIP: Quantization with Trellises and Incoherence Processing NIPS 2024
Inference for probabilistic dependency graphs UAI 2023
Random Laplacian Features for Learning with Hyperbolic Space ICLR 2023
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam ICLR 2023
STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition ICML 2023
CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks ICML 2023
InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models ICML 2023
Decentralized Learning: Theoretical Optimality and Practical Improvements JMLR 2023
Low-Precision Stochastic Gradient Langevin Dynamics ICML 2022
A General Analysis of Example-Selection for Stochastic Gradient Descent ICLR 2022
How Low Can We Go: Trading Memory for Error in Low-Precision Training ICLR 2022
Meta-Learning Divergences for Variational Inference AISTATS 2021
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision ICML 2021
Optimal Complexity in Decentralized Training ICML 2021
Variance Reduced Training with Stratified Sampling for Forecasting Models ICML 2021
โ€˜Tecnologica cosaโ€™: Modeling Storyteller Personalities in Boccaccioโ€™s โ€˜Decameronโ€™ EMNLP 2021
Differentiating through the Frรฉchet Mean ICML 2020
AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC AISTATS 2020
Moniqua: Modulo Quantized Communication in Decentralized SGD ICML 2020
Building Efficient Deep Neural Networks With Unitary Group Convolutions CVPR 2019
Accelerated Stochastic Power Iteration AISTATS 2018
Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling IJCAI 2017
Ensuring Rapid Mixing and Low Bias for Asynchronous Gibbs Sampling ICML 2016
Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems ICML 2015