Dheeraj Nagaraj

CoRR, 2024

Glauber Generative Model: Discrete Diffusion Models via Binary Classification.

[BibT_eX]

[DOI]

Harshit Varma

Karthikeyan Shanmugam

CoRR, 2024

A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health.

[BibT_eX]

[DOI]

CoRR, 2024

Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

Towards Zero Shot Learning in Restless Multi-armed Bandits.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

2023

Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization.

[BibT_eX]

[DOI]

CoRR, 2023

Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation.

[BibT_eX]

[DOI]

Aniket Das

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Multi-User Reinforcement Learning with Low Rank Rewards.

[BibT_eX]

[DOI]

Dheeraj Mysore Nagaraj

Proceedings of the International Conference on Machine Learning, 2023

Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms.

[BibT_eX]

[DOI]

Aniket Das

Anant Raj

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Near Optimal Heteroscedastic Regression with Symbiotic Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits.

[BibT_eX]

[DOI]

Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Expressivity and Structure in Networks: Ising Models, Random Graphs, and Neural Networks.

[BibT_eX]

[DOI]

PhD thesis, 2022

Entropic Convergence of Random Batch Methods for Interacting Particle Diffusion.

[BibT_eX]

[DOI]

CoRR, 2022

Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation.

[BibT_eX]

[DOI]

Ramnath Kumar

CoRR, 2022

Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs.

[BibT_eX]

[DOI]

Naman Agarwal

Syomantak Chaudhuri

Prateek Jain

Dheeraj Mysore Nagaraj

Praneeth Netrapalli

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Making the Last Iterate of SGD Information Theoretically Optimal.

[BibT_eX]

[DOI]

Prateek Jain

Praneeth Netrapalli

SIAM J. Optim., 2021

Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Streaming Linear System Identification with Reverse Experience Replay.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

The staircase property: How hierarchical structure can guide deep learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

A Law of Robustness for Two-Layers Neural Networks.

[BibT_eX]

[DOI]

Sébastien Bubeck

Yuanzhi Li

Proceedings of the Conference on Learning Theory, 2021

2020

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A Corrective View of Neural Networks: Representation, Memorization and Learning.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2020

2019

Phase Transitions for Detecting Latent Geometry in Random Graphs.

[BibT_eX]

[DOI]

Matthew S. Brennan

CoRR, 2019

SGD without Replacement: Sharper Rates for General Smooth Convex Functions.

[BibT_eX]

[DOI]

Prateek Jain

Praneeth Netrapalli

Proceedings of the 36th International Conference on Machine Learning, 2019

Open Problem: Do Good Algorithms Necessarily Query Bad Points?

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

2018

Optimal Single Sample Tests for Structured versus Unstructured Network Data.

[BibT_eX]

[DOI]