Niladri S. Chatterji
University of California, Berkeley
H-index: 18
North America-United States
Top articles of Niladri S. Chatterji
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
On the opportunities and risks of foundation models. arXiv 2021 | arXiv preprint arXiv:2108.07258 | Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora | 2021/8/16 |
Deep linear networks can benignly overfit when shallow ones do | Journal of Machine Learning Research | Niladri S Chatterji Philip M Long | 2023 |
Proving test set contamination in black box language models | arXiv preprint arXiv:2310.17623 | Yonatan Oren Nicole Meister Niladri Chatterji Faisal Ladhak Tatsunori B Hashimoto | 2023/10/26 |
Random feature amplification: Feature learning and generalization in neural networks | Journal of Machine Learning Research | Spencer Frei Niladri S Chatterji Peter L Bartlett | 2023 |
Oracle lower bounds for stochastic gradient sampling algorithms | Bernoulli | Niladri S Chatterji Peter L Bartlett Philip M Long | 2022/5 |
Holistic evaluation of language models | arXiv preprint arXiv:2211.09110 | Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu | 2022/11/16 |
Is importance weighting incompatible with interpolating classifiers? | arXiv preprint arXiv:2112.12986 | Ke Alexander Wang Niladri S Chatterji Saminul Haque Tatsunori Hashimoto | 2021/12/24 |
Benign overfitting without linearity: Neural network classifiers trained by gradient descent for noisy linear data | Spencer Frei Niladri S Chatterji Peter Bartlett | 2022/6/28 | |
Foolish crowds support benign overfitting | Journal of Machine Learning Research | Niladri S. Chatterji Philip M. Long | 2022 |
Undersampling is a minimax optimal robustness intervention in nonparametric classification | arXiv preprint arXiv:2205.13094 | Niladri S. Chatterji Saminul Haque Tatsunori Hashimoto | 2022/5/26 |
When does gradient descent with logistic loss find interpolating two-layer networks? | Journal of Machine Learning Research | Niladri S Chatterji Philip M Long Peter L Bartlett | 2021 |
The interplay between implicit bias and benign overfitting in two-layer linear networks | Journal of machine learning research | Niladri S Chatterji Philip M Long Peter L Bartlett | 2022 |
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? | Niladri S Chatterji Philip M Long Peter Bartlett | 2021/7/21 | |
Finite-sample analysis of interpolating linear classifiers in the overparameterized regime | Journal of Machine Learning Reseach | Niladri S. Chatterji Philip M. Long | 2021/5 |
Is there an analog of Nesterov acceleration for gradient-based MCMC? | Yi-An Ma Niladri S Chatterji Xiang Cheng Nicolas Flammarion Peter L Bartlett | 2021/5 | |
Why do gradient methods work in optimization and sampling? | Niladri S. Chatterji | 2021 | |
On the theory of reinforcement learning with once-per-episode feedback | Advances in Neural Information Processing Systems | Niladri Chatterji Aldo Pacchiano Peter Bartlett Michael Jordan | 2021/12/6 |
Langevin Monte Carlo without smoothness | Niladri Chatterji Jelena Diakonikolas Michael I Jordan Peter Bartlett | 2020/6/3 | |
OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits | Niladri Chatterji Vidya Muthukumar Peter Bartlett | 2020/6/3 | |
The intriguing role of module criticality in the generalization of deep networks | Niladri S. Chatterji Behnam Neyshabur Hanie Sedghi | 2020 |