Niladri S. Chatterji

发表

Finite-sample analysis of interpolating linear classifiers in the overparameterized regime pdf

Philip M. Long, Niladri S. Chatterji, 2020, ArXiv.

On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo pdf

Michael I. Jordan, Peter L. Bartlett, Yi-An Ma, 2018, ICML.

Oracle lower bounds for stochastic gradient sampling algorithms pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2020, Bernoulli.

When does gradient descent with logistic loss find interpolating two-layer networks? pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2020, J. Mach. Learn. Res..

The intriguing role of module criticality in the generalization of deep networks pdf

Behnam Neyshabur, Hanie Sedghi, Niladri S. Chatterji, 2020, ICLR.

Alternating minimization for dictionary learning with random initialization

Peter L. Bartlett, Niladri S. Chatterji, P. Bartlett, 2017, NIPS.

OSOM: A Simultaneously Optimal Algorithm for Multi-Armed and Linear Contextual Bandits

Peter L. Bartlett, Niladri S. Chatterji, Vidya Muthukumar, 2019, AISTATS.

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting pdf

Michael I. Jordan, Peter L. Bartlett, Yasin Abbasi-Yadkori, 2018, ArXiv.

Langevin Monte Carlo without Smoothness

Michael I. Jordan, Peter L. Bartlett, Jelena Diakonikolas, 2019, AISTATS.

Underdamped Langevin MCMC: A non-asymptotic analysis pdf

Michael I. Jordan, Peter L. Bartlett, Xiang Cheng, 2017, COLT.

Is There an Analog of Nesterov Acceleration for MCMC? pdf

Michael I. Jordan, Yi-An Ma, Xiang Cheng, 2019, ArXiv.

Fast Alternating Minimization Algorithms for Dictionary Learning

Peter L. Bartlett, Niladri S. Chatterji, 2017, NIPS 2017.

Online learning with kernel losses

Peter L. Bartlett, Aldo Pacchiano, Niladri S. Chatterji, 2018, ICML.

Is Importance Weighting Incompatible with Interpolating Classifiers? pdf

Niladri S. Chatterji, Saminul Haque, Tatsunori Hashimoto, 2021, ArXiv.

Foolish Crowds Support Benign Overfitting pdf

Niladri S. Chatterji, Philip M. Long, 2021, ArXiv.

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2021, COLT.

On the Theory of Reinforcement Learning with Once-per-Episode Feedback pdf

Michael I. Jordan, Peter L. Bartlett, Aldo Pacchiano, 2021, ArXiv.

The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2021, ArXiv.

Alternating minimization for dictionary learning: Local Convergence Guarantees

Niladri S. Chatterji, P. Bartlett, 2017 .

M L ] 3 0 M ay 2 01 9 Langevin Monte Carlo without Smoothness

Niladri S. Chatterji, 2019 .

Convergence Rates for Langevin Monte Carlo in the Nonconvex Setting

Michael I. Jordan, Niladri S. Chatterji, P. Bartlett, 2020 .

When does gradient descent with logistic loss find interpolating two-layer networks? pdf

Philip M. Long, Peter L. Bartlett, Niladri S. Chatterji, 2020, ArXiv.

Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification

Niladri S. Chatterji, Saminul Haque, Tatsunori Hashimoto, 2022, ArXiv.

Finite-sample analysis of interpolating linear classifiers in the overparameterized regime

Philip M. Long, Niladri S. Chatterji, 2020, J. Mach. Learn. Res..

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, COLT.

Deep Linear Networks can Benignly Overfit when Shallow Ones Do

Philip M. Long, Niladri S. Chatterji, 2022, ArXiv.

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Michael I. Jordan, Niladri S. Chatterji, P. Bartlett, 2021, NeurIPS.

The intriguing role of module criticality in the generalization of deep networks

Niladri S. Chatterji, Hanie Sedghi, Behnam Neyshabur, 2019, ICLR.

The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks

Philip M. Long, Niladri S. Chatterji, P. Bartlett, 2021, J. Mach. Learn. Res..

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, ArXiv.

Oracle lower bounds for stochastic gradient sampling algorithms

Philip M. Long, Niladri S. Chatterji, P. Bartlett, 2020, Bernoulli.

Is there an analog of Nesterov acceleration for gradient-based MCMC?

Michael I. Jordan, Niladri S. Chatterji, MA YI-AN, 2021 .

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.

Holistic Evaluation of Language Models

Christopher D. Manning, Sang Michael Xie, Niladri S. Chatterji, 2023, Annals of the New York Academy of Sciences.

Deep Linear Networks can Benignly Overfit when Shallow Ones Do

Philip M. Long, Niladri S. Chatterji, 2022, J. Mach. Learn. Res..

Is Importance Weighting Incompatible with Interpolating Classifiers?

Niladri S. Chatterji, Ke Alexander Wang, Saminul Haque, 2021, ICLR.

Foolish Crowds Support Benign Overfitting

Philip M. Long, Niladri S. Chatterji, Philip M. Long, 2021, J. Mach. Learn. Res..

Enhancement of Spin-transfer torque switching via resonant tunneling

Niladri S. Chatterji, A. Tulapurkar, B. Muralidharan, 2014, 1411.6454.

Plug-and-Play Representation Learning of Documents for Pre-trained Models

Niladri S. Chatterji, Kathleen A. Creel, Annie S. Chen, 2022 .

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, COLT.

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, ArXiv.

Holistic Evaluation of Language Models

Christopher D. Manning, Sang Michael Xie, Niladri S. Chatterji, 2023, Annals of the New York Academy of Sciences.

Proving Test Set Contamination in Black Box Language Models

Niladri S. Chatterji, Faisal Ladhak, Yonatan Oren, 2023, ArXiv.

Elastic Weight Consolidation for Reduction of Catastrophic Forgetting in GPT-2

Jose L. Part, Niladri S. Chatterji, Sydney von Arx, 2022 .

When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards

Mitesh M. Khapra, Isabel M. Kloumann, Niladri S. Chatterji, 2024, ArXiv.

On the Opportunities and Risks of Foundation Models

Michael S. Bernstein, Juan Carlos Niebles, Christopher D. Manning, 2021, ArXiv.