Deep double descent: Where bigger models and more data hurt P Nakkiran, G Kaplun, Y Bansal, T Yang, B Barak, I Sutskever Journal of Statistical Mechanics: Theory and Experiment 2021 (12), 124003, 2021 | 948 | 2021 |
Sgd on neural networks learns functions of increasing complexity P Nakkiran, G Kaplun, D Kalimeris, T Yang, BL Edelman, F Zhang, ... arXiv preprint arXiv:1905.11604, 2019 | 228* | 2019 |
For self-supervised learning, rationality implies generalization, provably Y Bansal, G Kaplun, B Barak arXiv preprint arXiv:2010.08508, 2020 | 28 | 2020 |
Deconstructing distributions: A pointwise framework of learning G Kaplun, N Ghosh, S Garg, B Barak, P Nakkiran arXiv preprint arXiv:2202.09931, 2022 | 19 | 2022 |
Robust Influence Maximization for Hyperparametric Models D Kalimeris, G Kaplun, Y Singer ICML 2019, 2019 | 18 | 2019 |
Robust neural networks are more interpretable for genomics PK Koo, S Qian, G Kaplun, V Volf, D Kalimeris bioRxiv, 657437, 2019 | 12 | 2019 |
Knowledge distillation: Bad models can be good role models G Kaplun, E Malach, P Nakkiran, S Shalev-Shwartz Advances in Neural Information Processing Systems 35, 28683-28694, 2022 | 10 | 2022 |
For manifold learning, deep neural networks can be locality sensitive hash functions N Dikkala, G Kaplun, R Panigrahy arXiv preprint arXiv:2103.06875, 2021 | 7 | 2021 |
Subtuning: Efficient finetuning for multi-task learning G Kaplun, A Gurevich, T Swisa, M David, S Shalev-Shwartz, E Malach arXiv e-prints, arXiv: 2302.06354, 2023 | 5 | 2023 |
Robustness from simple classifiers S Qian, D Kalimeris, G Kaplun, Y Singer arXiv preprint arXiv:2002.09422, 2020 | 3 | 2020 |
Remote inspection of adversary-controlled environments J Tobisch, S Philippe, B Barak, G Kaplun, C Zenger, A Glaser, C Paar, ... Nature communications 14 (1), 6566, 2023 | 2 | 2023 |
Beyond implicit bias: The insignificance of sgd noise in online learning N Vyas, D Morwani, R Zhao, G Kaplun, S Kakade, B Barak arXiv preprint arXiv:2306.08590, 2023 | 2 | 2023 |
Less is More: Selective Layer Finetuning with SubTuning G Kaplun, A Gurevich, T Swisa, M David, S Shalev-Shwartz, E Malach arXiv preprint arXiv:2302.06354, 2023 | 1 | 2023 |
Implicit Intermediate Supervision for Learning Complex Functions G Kaplun, N Wies | | 2023 |
Corgi^ 2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD E Livne, G Kaplun, EM Shai arXiv preprint arXiv:2309.01640, 2023 | | 2023 |
On Scaling Dynamics in Deep Learning G Kaplun Harvard University, 2023 | | 2023 |