Follow
Niladri S. Chatterji
Niladri S. Chatterji
Postdoctoral Researcher, Department of Computer Science, Stanford University
Verified email at cs.stanford.edu - Homepage
Title
Cited by
Cited by
Year
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
4502021
Underdamped Langevin MCMC: A non-asymptotic analysis
X Cheng, NS Chatterji, PL Bartlett, MI Jordan
Conference on Learning Theory 75, 300--323, 2018
2162018
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
1342018
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
99*2021
On the theory of variance reduction for stochastic gradient Monte Carlo
NS Chatterji, N Flammarion, YA Ma, PL Bartlett, MI Jordan
International Conference on Machine Learning 80, 764--773, 2018
872018
Finite-sample analysis of interpolating linear classifiers in the overparameterized regime
NS Chatterji, PM Long
Journal of Machine Learning Reseach 22 (129), 1--30, 2021
642021
OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits
NS Chatterji, V Muthukumar, PL Bartlett
International Conference on Artificial Intelligence and Statistics 108, 1844 …, 2020
342020
The intriguing role of module criticality in the generalization of deep networks
NS Chatterji, B Neyshabur, H Sedghi
International Conference on Learning Representations, 2020
302020
Alternating minimization for dictionary learning with random initialization
NS Chatterji, PL Bartlett
Advances in Neural Information Processing Systems 30, 2017
302017
Enhancement of spin-transfer torque switching via resonant tunneling
NS Chatterji, AA Tulapurkar, B Muralidharan
Applied Physics Letters 105 (23), 232410, 2014
302014
Langevin Monte Carlo without smoothness
NS Chatterji, J Diakonikolas, MI Jordan, PL Bartlett
International Conference on Artificial Intelligence and Statistics 108, 1716 …, 2020
272020
Benign overfitting without linearity: Neural network classifiers trained by gradient descent for noisy linear data
S Frei, NS Chatterji, PL Bartlett
Conference on Learning Theory 178, 2668--2703, 2022
202022
Online learning with kernel losses
NS Chatterji, A Pacchiano, PL Bartlett
International Conference on Machine Learning 97, 971--980, 2019
15*2019
The interplay between implicit bias and benign overfitting in two-layer linear networks
NS Chatterji, PM Long, PL Bartlett
Journal of Machine Learning Research 23 (263), 1--48, 2021
112021
Is importance weighting incompatible with interpolating classifiers?
KA Wang, NS Chatterji, S Haque, T Hashimoto
International Conference on Learning Representations, 2022
92022
On the theory of reinforcement learning with once-per-episode feedback
NS Chatterji, A Pacchiano, PL Bartlett, MI Jordan
Advances in Neural Information Processing Systems 34, 3401--3412, 2021
92021
When does gradient descent with logistic loss find interpolating two-layer networks?
NS Chatterji, PM Long, PL Bartlett
Journal of Machine Learning Research 22, 1--48, 2021
92021
Foolish crowds support benign overfitting
NS Chatterji, PM Long
Journal of Machine Learning Research 23 (125), 1--12, 2022
82022
Random feature amplification: Feature learning and generalization in neural networks
S Frei, NS Chatterji, PL Bartlett
arXiv preprint arXiv:2202.07626, 2022
62022
Oracle lower bounds for stochastic gradient sampling algorithms
NS Chatterji, PL Bartlett, PM Long
Bernoulli 28 (2), 1074 -- 1092, 2022
62022
The system can't perform the operation now. Try again later.
Articles 1–20