Yair Carmon

Publication Activity (10 Years)

Years Active: 2008-2024
Publications (10 Years): 68

Top Topics

Convex Optimization

Top Venues

Publications

Itai Kreisler, Maor Ivgi, Oliver Hinder, Yair Carmon
Accelerated Parameter-Free Stochastic Optimization. CoRR (2024)
Yair Carmon, Oliver Hinder
The Price of Adaptivity in Stochastic Convex Optimization. CoRR (2024)
Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Yitzhak Gadre, Hritik Bansal, Etash Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah M. Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Raghavi Chandu, Thao Nguyen, Igor Vasiljevic, Sham M. Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G. Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar
DataComp-LM: In search of the next generation of training sets for language models. CoRR (2024)
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
A Whole New Ball Game: A Primal Accelerated Method for Matrix Games and Minimizing the Maximum of Smooth Functions. SODA (2024)
Itai Kreisler, Maor Ivgi, Oliver Hinder, Yair Carmon
Accelerated Parameter-Free Stochastic Optimization. COLT (2024)
Yair Carmon, Oliver Hinder
The Price of Adaptivity in Stochastic Convex Optimization. COLT (2024)
Tomer Porian, Mitchell Wortsman, Jenia Jitsev, Ludwig Schmidt, Yair Carmon
Resolving Discrepancies in Compute-Optimal Scaling of Language Models. CoRR (2024)
Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Jenia Jitsev, Alexandros G. Dimakis, Gabriel Ilharco, Shuran Song, Thomas Kollar, Yair Carmon, Achal Dave, Reinhard Heckel, Niklas Muennighoff, Ludwig Schmidt
Language models scale reliably with over-training and on downstream tasks. CoRR (2024)
Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry, Yair Carmon
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond. CoRR (2023)
Maor Ivgi, Oliver Hinder, Yair Carmon
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule. CoRR (2023)
Itai Kreisler, Mor Shpigel Nacson, Daniel Soudry, Yair Carmon
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond. ICML (2023)
Yair Carmon, Arun Jambulapati, Yujia Jin, Yin Tat Lee, Daogao Liu, Aaron Sidford, Kevin Tian
ReSQueing Parallel and Private Stochastic Convex Optimization. CoRR (2023)
Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah M. Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
DataComp: In search of the next generation of multimodal datasets. CoRR (2023)
Yoav Wald, Gal Yona, Uri Shalit, Yair Carmon
Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds. ICLR (2023)
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
A Whole New Ball Game: A Primal Accelerated Method for Matrix Games and Minimizing the Maximum of Smooth Functions. CoRR (2023)
Yair Carmon, Arun Jambulapati, Yujia Jin, Yin Tat Lee, Daogao Liu, Aaron Sidford, Kevin Tian
ReSQueing Parallel and Private Stochastic Convex Optimization. FOCS (2023)
Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah M. Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander J. Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
DataComp: In search of the next generation of multimodal datasets. NeurIPS (2023)
Maor Ivgi, Oliver Hinder, Yair Carmon
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule. ICML (2023)
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Nathan Srebro, Blake E. Woodworth
Lower bounds for non-convex stochastic optimization. Math. Program. 199 (1) (2023)
Yair Carmon, Danielle Hausler
Distributionally Robust Optimization via Ball Oracle Acceleration. NeurIPS (2022)
Yair Carmon, Danielle Hausler, Arun Jambulapati, Yujia Jin, Aaron Sidford
Optimal and Adaptive Monteiro-Svaiter Acceleration. CoRR (2022)
Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. ICML (2022)
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization. CoRR (2022)
Maor Ivgi, Yair Carmon, Jonathan Berant
Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments. EMNLP (Findings) (2022)
Yoav Wald, Gal Yona, Uri Shalit, Yair Carmon
Malign Overfitting: Interpolation Can Provably Preclude Invariance. CoRR (2022)
Yair Carmon, Danielle Hausler, Arun Jambulapati, Yujia Jin, Aaron Sidford
Optimal and Adaptive Monteiro-Svaiter Acceleration. NeurIPS (2022)
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization. ICML (2022)
Yair Carmon, Oliver Hinder
Making SGD Parameter-Free. COLT (2022)
Maor Ivgi, Yair Carmon, Jonathan Berant
Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments. CoRR (2022)
Yair Carmon, Danielle Hausler
Distributionally Robust Optimization via Ball Oracle Acceleration. CoRR (2022)
Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. CoRR (2022)
Yair Carmon, Oliver Hinder
Making SGD Parameter-Free. CoRR (2022)
Hilal Asi, Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
Stochastic Bias-Reduced Gradient Methods. CoRR (2021)
Yair Carmon, John C. Duchi, Oliver Hinder, Aaron Sidford
Lower bounds for finding stationary points II: first-order methods. Math. Program. 185 (1-2) (2021)
Idan Amir, Yair Carmon, Tomer Koren, Roi Livni
Never Go Full Batch (in Stochastic Convex Optimization). CoRR (2021)
Idan Amir, Yair Carmon, Tomer Koren, Roi Livni
Never Go Full Batch (in Stochastic Convex Optimization). NeurIPS (2021)
John Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, Ludwig Schmidt
Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization. CoRR (2021)
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss. COLT (2021)
John P. Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, Ludwig Schmidt
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization. ICML (2021)
Hilal Asi, Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
Stochastic Bias-Reduced Gradient Methods. NeurIPS (2021)
Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford
Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss. CoRR (2021)
Yair Carmon, Arun Jambulapati, Qijia Jiang, Yujia Jin, Yin Tat Lee, Aaron Sidford, Kevin Tian
Acceleration with a Ball Optimization Oracle. NeurIPS (2020)
Yair Carmon, Yujia Jin, Aaron Sidford, Kevin Tian
Coordinate Methods for Matrix Games. FOCS (2020)
Daniel Levy, Yair Carmon, John C. Duchi, Aaron Sidford
Large-Scale Methods for Distributionally Robust Optimization. CoRR (2020)
Yair Carmon, Yujia Jin, Aaron Sidford, Kevin Tian
Coordinate Methods for Matrix Games. CoRR (2020)
Yair Carmon, John C. Duchi, Oliver Hinder, Aaron Sidford
Lower bounds for finding stationary points I. Math. Program. 184 (1) (2020)
Yair Carmon, John C. Duchi
First-Order Methods for Nonconvex Quadratic Minimization. SIAM Rev. 62 (2) (2020)
Daniel Levy, Yair Carmon, John C. Duchi, Aaron Sidford
Large-Scale Methods for Distributionally Robust Optimization. NeurIPS (2020)
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations. COLT (2020)
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations. CoRR (2020)
Yair Carmon, Arun Jambulapati, Qijia Jiang, Yujia Jin, Yin Tat Lee, Aaron Sidford, Kevin Tian
Acceleration with a Ball Optimization Oracle. CoRR (2020)
Yair Carmon, John C. Duchi, Aaron Sidford, Kevin Tian
A Rank-1 Sketch for Matrix Multiplicative Weights. COLT (2019)
Yair Carmon, Aditi Raghunathan, Ludwig Schmidt, Percy Liang, John C. Duchi
Unlabeled Data Improves Adversarial Robustness. CoRR (2019)
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Nathan Srebro, Blake E. Woodworth
Lower Bounds for Non-Convex Stochastic Optimization. CoRR (2019)
Yair Carmon, John C. Duchi
Gradient Descent Finds the Cubic-Regularized Nonconvex Newton Step. SIAM J. Optim. 29 (3) (2019)
Yair Carmon, Yujia Jin, Aaron Sidford, Kevin Tian
Variance Reduction for Matrix Games. NeurIPS (2019)
Yair Carmon, John C. Duchi, Aaron Sidford, Kevin Tian
A Rank-1 Sketch for Matrix Multiplicative Weights. CoRR (2019)
Yair Carmon, Aditi Raghunathan, Ludwig Schmidt, John C. Duchi, Percy Liang
Unlabeled Data Improves Adversarial Robustness. NeurIPS (2019)
Yair Carmon, Yujia Jin, Aaron Sidford, Kevin Tian
Variance Reduction for Matrix Games. CoRR (2019)
Yair Carmon, John C. Duchi, Oliver Hinder, Aaron Sidford
Accelerated Methods for NonConvex Optimization. SIAM J. Optim. 28 (2) (2018)
Yair Carmon, John C. Duchi
Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems. NeurIPS (2018)
Yair Carmon, John C. Duchi, Oliver Hinder, Aaron Sidford
"Convex Until Proven Guilty": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions. ICML (2017)
Kartik Venkat, Tsachy Weissman, Yair Carmon, Shlomo Shamai
Information, Estimation, and Lookahead in the Gaussian Channel. IEEE Trans. Signal Process. 64 (14) (2016)
Yair Carmon, John C. Duchi
Gradient Descent Efficiently Finds the Cubic-Regularized Non-Convex Newton Step. CoRR (2016)
Daniel Soudry, Yair Carmon
No bad local minima: Data independent training error guarantees for multilayer neural networks. CoRR (2016)
Yair Carmon, John C. Duchi, Oliver Hinder, Aaron Sidford
Accelerated Methods for Non-Convex Optimization. CoRR (2016)
Yair Carmon, Shlomo Shamai
Lower Bounds and Approximations for the Information Rate of the ISI Channel. IEEE Trans. Inf. Theory 61 (10) (2015)
Yair Carmon, Shlomo Shamai, Tsachy Weissman
Comparison of the Achievable Rates in OFDM and Single Carrier Modulation with I.I.D. Inputs. IEEE Trans. Inf. Theory 61 (4) (2015)
Yair Carmon, Shlomo Shamai
Lower Bounds and Approximations for the Information Rate of the ISI Channel. CoRR (2014)
Kartik Venkat, Tsachy Weissman, Yair Carmon, Shlomo Shamai
Information, Estimation, and Lookahead in the Gaussian channel CoRR (2013)
Yair Carmon, Shlomo Shamai, Tsachy Weissman
Comparison of the Achievable Rates in OFDM and Single Carrier Modulation with I.I.D. Inputs. CoRR (2013)
Kartik Venkat, Tsachy Weissman, Yair Carmon, Shlomo Shamai
The role of lookahead in estimation under Gaussian noise. ISIT (2013)
Kartik Venkat, Tsachy Weissman, Yair Carmon, Shlomo Shamai
On information, estimation and lookahead. Allerton Conference (2012)
Alexander M. Bronstein, Michael M. Bronstein, Yair Carmon, Ron Kimmel
Partial Similarity of Shapes Using a Statistical Significance Measure. IPSJ Trans. Comput. Vis. Appl. 1 (2009)
Yair Carmon, Adam Shwartz
Markov decision processes with exponentially representable discounting. Oper. Res. Lett. 37 (1) (2009)
Yair Carmon, Adam Shwartz
Eventually-stationary policies for Markov decision models with non-constant discounting. VALUETOOLS (2008)