Manuscripts:
- Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization (2023)
arXiv preprint
with Ramnath Kumar, Kushal Majmundar and Arun Suggala - Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation (2022)
arXiv preprint
with Ramnath Kumar
Conference Publications:
- Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation (2023)
NeurIPS 2023 [Spotlight]
with Aniket Das - Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms
COLT 2023
with Aniket Das and Anant Raj - Near Optimal Heteroscedastic Regression with Symbiotic Learning
COLT 2023
with Dheeraj Baby, Aniket Das and Praneeth Netrapalli - Multi-User Reinforcement Learning with Low Rank Rewards
ICML 2023
with Naman Agarwal, Prateek Jain, Suhas Kowshik and Praneeth Netrapalli - Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
AISTATS 2023
with Gandharv Patil, L A Prashanth and Doina Precup - Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits
AAMAS 2023
with Abheek Ghosh, Manish Jain and Milind Tambe - Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs
ICLR 2022
with Naman Agarwal, Syomantak Chaudhuri, Prateek Jain and Praneeth Netrapalli.
- Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems. (2021)
NeurIPS 2021 (spotlight)
with Prateek Jain, Suhas Kowshik and Praneeth Netrapalli. - Streaming Linear System Identification with Reverse Experience Replay (2021)
NeurIPS 2021
with Prateek Jain, Suhas Kowshik and Praneeth Netrapalli.
- The staircase property: How hierarchical structure can guide deep learning. (2021)
NeurIPS 2021
with Emmanuel Abbe, Enric Boix-Adsera, Matthew Brennan and Guy Bresler - A Law of Robustness for Two-Layers Neural Networks. (2020)
COLT 2021
with Sébastien Bubeck and Yuanzhi Li - Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth. (2020)
NeurIPS 2020
with Guy Bresler.
- Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms. (2020)
NeurIPS 2020 (spotlight)
with Guy Bresler, Prateek Jain, Praneeth Netrapalli, Xian Wu
- A Corrective View of Neural Networks: Representation, Memorization and Learning. (2020)
COLT 2020
arXiv preprint : arxiv:2002.00274
with Guy Bresler. - SGD without Replacement: Sharper Rates for General Smooth Convex Functions. (2019)
ICML 2019
with Praneeth Netrapalli and Prateek Jain - Optimal Single Sample Tests for Structured versus Unstructured Network Data. (2018)
COLT 2018.
arXiv preprint : arxiv:1802.06186
with Guy Bresler
Journal Publications:
- Metastable Mixing of Markov Chains: Efficiently Sampling Low Temperature Exponential Random Graphs (2023+)
Annals of Applied Probability, to appear
with Guy Bresler and Eshaan Nichani
- Making Last Iterate of Stochastic Gradient Descent Information Theoretically Optimal. (2021)
SIAM Journal on Optimization (2021) , COLT 2019 (extended abstract)
with Praneeth Netrapalli and Prateek Jain - Phase Transition for Detecting Latent Geometry in Random Graphs. (2020)
Probability Theory and Related Fields
arXiv preprint: arxiv:1910.14167
with Matthew Brennan and Guy Bresler - Stein’s Method for Stationary Distributions of Markov Chains and Application to Ising Models. (2019)
Annals of Applied Probability
arXiv preprint: arxiv:1712.05743,
with Guy Bresler - Continuous limit of discrete quantum walks. (2015)
Physical Review A, arxiv:1501.06950
with Todd A. Brun