| On the opportunities and risks of foundation models R Bommasani, DA Hudson, E Adeli, R Altman, S Arora, S von Arx, ... arXiv preprint arXiv:2108.07258, 2021 | 295 | 2021 |
| Underdamped Langevin MCMC: A non-asymptotic analysis X Cheng, NS Chatterji, PL Bartlett, MI Jordan arXiv preprint arXiv:1707.03663, 2017 | 191 | 2017 |
| Sharp convergence rates for Langevin dynamics in the nonconvex setting X Cheng, NS Chatterji, Y Abbasi-Yadkori, PL Bartlett, MI Jordan arXiv preprint arXiv:1805.01648, 2018 | 118 | 2018 |
| Is there an analog of Nesterov acceleration for gradient-based MCMC? YA Ma, NS Chatterji, X Cheng, N Flammarion, PL Bartlett, MI Jordan Bernoulli 27 (3), 1942-1992, 2021 | 86* | 2021 |
| On the theory of variance reduction for stochastic gradient Monte Carlo N Chatterji, N Flammarion, Y Ma, P Bartlett, M Jordan International Conference on Machine Learning, 764-773, 2018 | 84 | 2018 |
| Finite-sample analysis of interpolating linear classifiers in the overparameterized regime NS Chatterji, M Long, Philip arXiv preprint arXiv:2004.12019 16, 2020 | 51 | 2020 |
| Osom: A simultaneously optimal algorithm for multi-armed and linear contextual bandits N Chatterji, V Muthukumar, P Bartlett International Conference on Artificial Intelligence and Statistics, 1844-1854, 2020 | 32 | 2020 |
| Alternating minimization for dictionary learning: Local convergence guarantees NS Chatterji, PL Bartlett arXiv preprint arXiv:1711.03634, 2017 | 30* | 2017 |
| Enhancement of Spin-transfer torque switching via resonant tunneling N Chatterji, AA Tulapurkar, B Muralidharan Applied Physics Letters 105 (23), 232410, 2014 | 30 | 2014 |
| The intriguing role of module criticality in the generalization of deep networks NS Chatterji, B Neyshabur, H Sedghi arXiv preprint arXiv:1912.00528, 2019 | 26 | 2019 |
| Langevin monte carlo without smoothness N Chatterji, J Diakonikolas, MI Jordan, P Bartlett International Conference on Artificial Intelligence and Statistics, 1716-1726, 2020 | 24 | 2020 |
| Online learning with kernel losses N Chatterji, A Pacchiano, P Bartlett International Conference on Machine Learning, 971-980, 2019 | 14* | 2019 |
| On the theory of reinforcement learning with once-per-episode feedback N Chatterji, A Pacchiano, P Bartlett, M Jordan Advances in Neural Information Processing Systems 34, 3401-3412, 2021 | 8 | 2021 |
| When does gradient descent with logistic loss find interpolating two-layer networks? NS Chatterji, PM Long, PL Bartlett J. Mach. Learn. Res. 22, 159:1-159:48, 2021 | 8 | 2021 |
| Benign overfitting without linearity: Neural network classifiers trained by gradient descent for noisy linear data S Frei, NS Chatterji, P Bartlett Conference on Learning Theory, 2668-2703, 2022 | 6 | 2022 |
| Foolish Crowds Support Benign Overfitting NS Chatterji, PM Long Journal of Machine Learning Research 23 (125), 1-12, 2022 | 6 | 2022 |
| Is Importance Weighting Incompatible with Interpolating Classifiers? KA Wang, NS Chatterji, S Haque, T Hashimoto arXiv preprint arXiv:2112.12986, 2021 | 6 | 2021 |
| Oracle lower bounds for stochastic gradient sampling algorithms NS Chatterji, PL Bartlett, PM Long arXiv preprint arXiv:2002.00291, 2020 | 5 | 2020 |
| Random feature amplification: Feature learning and generalization in neural networks S Frei, NS Chatterji, PL Bartlett arXiv preprint arXiv:2202.07626, 2022 | 3 | 2022 |
| The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks NS Chatterji, PM Long, PL Bartlett arXiv preprint arXiv:2108.11489, 2021 | 3 | 2021 |
Peter BartlettProfessor, EECS and Statistics, UC BerkeleyVerified email at cs.berkeley.edu
