| Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time M Wortsman, G Ilharco, SY Gadre, R Roelofs, R Gontijo-Lopes, ... International conference on machine learning, 23965-23998, 2022 | 987 | 2022 |
| Unlabeled data improves adversarial robustness Y Carmon, A Raghunathan, L Schmidt, JC Duchi, PS Liang Advances in neural information processing systems 32, 2019 | 852 | 2019 |
| Lower bounds for non-convex stochastic optimization Y Arjevani, Y Carmon, JC Duchi, DJ Foster, N Srebro, B Woodworth Mathematical Programming 199 (1), 165-214, 2023 | 403 | 2023 |
| Datacomp: In search of the next generation of multimodal datasets SY Gadre, G Ilharco, A Fang, J Hayase, G Smyrnis, T Nguyen, R Marten, ... Advances in Neural Information Processing Systems 36, 27092-27112, 2023 | 382 | 2023 |
| Accelerated methods for nonconvex optimization Y Carmon, JC Duchi, O Hinder, A Sidford SIAM Journal on Optimization 28 (2), 1751-1772, 2018 | 368 | 2018 |
| Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization JP Miller, R Taori, A Raghunathan, S Sagawa, PW Koh, V Shankar, ... International conference on machine learning, 7721-7735, 2021 | 319 | 2021 |
| Lower bounds for finding stationary points I Y Carmon, JC Duchi, O Hinder, A Sidford Mathematical Programming, 1-50, 2019 | 301 | 2019 |
| No bad local minima: Data independent training error guarantees for multilayer neural networks D Soudry, Y Carmon arXiv preprint arXiv:1605.08361, 2016 | 273 | 2016 |
| Large-scale methods for distributionally robust optimization D Levy, Y Carmon, JC Duchi, A Sidford Advances in Neural Information Processing Systems 33, 8847-8860, 2020 | 259 | 2020 |
| "Convex Until Proven Guilty": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions Y Carmon, O Hinder, JC Duchi, A Sidford arXiv preprint arXiv:1705.02766, 2017 | 180 | 2017 |
| Gradient descent finds the cubic-regularized non-convex newton step Y Carmon, JC Duchi arXiv preprint arXiv:1612.00547, 2016 | 179 | 2016 |
| Lower bounds for finding stationary points II: first-order methods Y Carmon, JC Duchi, O Hinder, A Sidford Mathematical Programming, 2019 | 172* | 2019 |
| Variance reduction for matrix games Y Carmon, Y Jin, A Sidford, K Tian Advances in Neural Information Processing Systems 32, 2019 | 85 | 2019 |
| Second-order information in non-convex stochastic optimization: Power and limitations Y Arjevani, Y Carmon, JC Duchi, DJ Foster, A Sekhari, K Sridharan Conference on Learning Theory, 242-299, 2020 | 65 | 2020 |
| DoG is SGD’s best friend: A parameter-free dynamic step size schedule M Ivgi, O Hinder, Y Carmon International Conference on Machine Learning, 14465-14499, 2023 | 62 | 2023 |
| Analysis of Krylov Subspace Solutions of Regularized Nonconvex Quadratic Problems Y Carmon, JC Duchi arXiv preprint arXiv:1806.09222, 2018, 2018 | 59 | 2018 |
| Contour based defect detection A Gupta, M Mahadevan, S Venkataraman, H Yang, L Karsenti, Y Carmon, ... US Patent 10,395,362, 2019 | 56 | 2019 |
| Datacomp-lm: In search of the next generation of training sets for language models J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, SY Gadre, H Bansal, E Guha, ... Advances in Neural Information Processing Systems 37, 14200-14282, 2025 | 55 | 2025 |
| Single image detection L Karsenti, K Bhaskar, JR Jordan III, S Venkataraman, Y Carmon US Patent 10,186,026, 2019 | 52 | 2019 |
| Harder or different? a closer look at distribution shift in dataset reproduction S Lu, B Nott, A Olson, A Todeschini, H Vahabi, Y Carmon, L Schmidt ICML Workshop on Uncertainty and Robustness in Deep Learning 5, 15, 2020 | 51 | 2020 |
John DuchiAssociate Professor of Statistics and Electrical Engineering, Stanford Universityכתובת אימייל מאומתת בדומיין stanford.edu