← Authors

Yair Carmon

27 papers · 2017–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (8) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (34) 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (8) 🌈 Renaissance Researcher (5) πŸ‘₯ Mega-Team (60) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (13) ⚑ Prolific Year (6) πŸ“ˆ Trend Setter πŸ’Ž Century Club (27) πŸ—ƒοΈ Keyword Collector (98) πŸ”₯ Unstoppable (9)

Conferences

NIPS (12) COLT (6) ICML (6) ICLR (2) EMNLP (1)

Top co-authors

Aaron Sidford (8) Ludwig Schmidt (7) Yujia Jin (6) Arun Jambulapati (5) Oliver Hinder (5) John C. Duchi (5) Mitchell Wortsman (5) Jenia Jitsev (4) Vaishaal Shankar (4) Gabriel Ilharco (4)

Keywords

convex optimization (7) stochastic convex optimization (4) gradient descent (4) accelerated gradient (3) oracle complexity (3) parameter-free optimization (3) neural network optimization (3) data filtering (2) second-order method (2) multilevel monte carlo (2) stochastic gradient descent (2) distributionally robust optimization (2) stochastic method (2) lipschitz function (2) loss landscape (2) language model (2) non-convex optimization (2) stochastic optimization (2) convex loss (2) scaling law (2)

Papers

Language models scale reliably with over-training and on downstream tasks ICLR 2025
The Price of Adaptivity in Stochastic Convex Optimization COLT 2024
Resolving Discrepancies in Compute-Optimal Scaling of Language Models NIPS 2024
DataComp-LM: In search of the next generation of training sets for language models NIPS 2024
Accelerated Parameter-Free Stochastic Optimization COLT 2024
Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds ICLR 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023
DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule ICML 2023
DataComp: In search of the next generation of multimodal datasets NIPS 2023
Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments EMNLP 2022
Optimal and Adaptive Monteiro-Svaiter Acceleration NIPS 2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time ICML 2022
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization ICML 2022
Making SGD Parameter-Free COLT 2022
Distributionally Robust Optimization via Ball Oracle Acceleration NIPS 2022
Never Go Full Batch (in Stochastic Convex Optimization) NIPS 2021
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ICML 2021
Stochastic Bias-Reduced Gradient Methods NIPS 2021
Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss COLT 2021
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations COLT 2020
Large-Scale Methods for Distributionally Robust Optimization NIPS 2020
Acceleration with a Ball Optimization Oracle NIPS 2020
A Rank-1 Sketch for Matrix Multiplicative Weights COLT 2019
Variance Reduction for Matrix Games NIPS 2019
Unlabeled Data Improves Adversarial Robustness NIPS 2019
Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems NIPS 2018
β€œConvex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions ICML 2017