| Gradient descent GAN optimization is locally stable V Nagarajan, JZ Kolter Advances in Neural Information Processing Systems, 5585-5595, 2017 | 386 | 2017 |
| Uniform convergence may be unable to explain generalization in deep learning V Nagarajan, JZ Kolter Advances in Neural Information Processing Systems, 2019 | 300 | 2019 |
| Understanding the Failure Modes of Out-of-Distribution Generalization V Nagarajan, A Andreassen, B Neyshabur International Conference on Learning Representations (ICLR) 2021, 2020 | 164 | 2020 |
| Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience V Nagarajan, Z Kolter International Conference on Learning Representations, 2019, 2018 | 107 | 2018 |
| Assessing Generalization via Disagreement Y Jiang, V Nagarajan, C Baek, JZ Kolter International Conference on Learning Representations, 2022, 2021 | 106* | 2021 |
| Generalization in deep networks: The role of distance from initialization V Nagarajan, JZ Kolter arXiv preprint arXiv:1901.01672, 2019 | 94 | 2019 |
| Learning-theoretic foundations of algorithm configuration for combinatorial partitioning problems MF Balcan, V Nagarajan, E Vitercik, C White Conference on Learning Theory, 213-274, 2016 | 61 | 2016 |
| Geriatrix: Aging what you see and what you don’t see. A file system aging approach for modern storage systems S Kadekodi, V Nagarajan, GR Ganger, GA Gibson Proceedings of the 2018 USENIX Conference on Usenix Annual Technical …, 2018 | 45 | 2018 |
| Theoretical Insights into Memorization in GANs V Nagarajan, C Raffel, IJ Goodfellow Integration of Deep Learning Theories Workshop, 32nd Conference on Neural …, 2018 | 32 | 2018 |
| Revisiting Adversarial Risk AS Suggala, A Prasad, V Nagarajan, P Ravikumar The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 30 | 2019 |
| A Learning Theoretic Perspective on Local Explainability J Li, V Nagarajan, G Plumb, A Talwalkar International Conference on Learning Representations (ICLR) 2021, 2020 | 18 | 2020 |
| Think before you speak: Training language models with pause tokens S Goyal, Z Ji, AS Rawat, AK Menon, S Kumar, V Nagarajan arXiv preprint arXiv:2310.02226, 2023 | 17 | 2023 |
| Incorporating side information in tensor completion H Lamba, V Nagarajan, K Shin, N Shajarisales Proceedings of the 25th International Conference Companion on World Wide Web …, 2016 | 17 | 2016 |
| Every team deserves a second chance: Identifying when things go wrong V Nagarajan, L Soriano Marcolino, M Tambe Proceedings of the 2015 International Conference on Autonomous Agents and …, 2015 | 16* | 2015 |
| Provably Safe PAC-MDP Exploration Using Analogies M Roderick, V Nagarajan, JZ Kolter Proceedings of the 24th International Conference on Artificial Intelligence …, 2020 | 12 | 2020 |
| Explaining generalization in deep learning: progress and fundamental limits V Nagarajan arXiv preprint arXiv:2110.08922, 2021 | 10 | 2021 |
| A Reinforcement learning approach to online learning of decision trees A Garlapati, A Raghunathan, V Nagarajan, B Ravindran arXiv preprint arXiv:1507.06923, 2015 | 9 | 2015 |
| The pitfalls of next-token prediction G Bachmann, V Nagarajan arXiv preprint arXiv:2403.06963, 2024 | 6 | 2024 |
| ResMem: Learn what you can and memorize the rest Z Yang, M Lukasik, V Nagarajan, Z Li, AS Rawat, M Zaheer, AK Menon, ... arXiv preprint arXiv:2302.01576, 2023 | 5 | 2023 |
| On student-teacher deviations in distillation: does it pay to disobey? V Nagarajan, AK Menon, S Bhojanapalli, H Mobahi, S Kumar arXiv preprint arXiv:2301.12923, 2023 | 4 | 2023 |
Zico KolterCarnegie Mellon University在 cs.cmu.edu 的电子邮件经过验证
