Rohatgi, Dhruv

20 publications

ICLR 2026 Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking Dhruv Rohatgi, Abhishek Shetty, Donya Saless, Yuchen Li, Ankur Moitra, Andrej Risteski, Dylan J Foster

COLT 2025 Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning Under Misspecification (extended Abstract) Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster

COLT 2025 Is a Good Foundation Necessary for Efficient Reinforcement Learning? the Computational Role of the Base Model in Exploration Dylan J Foster, Zakaria Mhammedi, Dhruv Rohatgi

COLT 2025 Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning Dhruv Rohatgi, Dylan J. Foster

ICLR 2025 Self-Improvement in Language Models: The Sharpening Mechanism Audrey Huang, Adam Block, Dylan J Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

NeurIPS 2025 To Distill or Decide? Understanding the Algorithmic Trade-Off in Partially Observable RL Yuda Song, Dhruv Rohatgi, Aarti Singh, Drew Bagnell

ICML 2025 Towards Characterizing the Value of Edge Embeddings in Graph Neural Networks Dhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu, Ankur Moitra, Andrej Risteski

COLT 2024 Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps Jonathan Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi

NeurIPS 2024 Online Control in Population Dynamics Noah Golowich, Elad Hazan, Zhou Lu, Dhruv Rohatgi, Y. Jennifer Sun

NeurIPSW 2024 Self-Improvement in Language Models: The Sharpening Mechanism Audrey Huang, Adam Block, Dylan J Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

NeurIPSW 2024 Towards Characterizing the Value of Edge Embeddings in Graph Neural Networks Dhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu, Ankur Moitra, Andrej Risteski

NeurIPS 2023 Feature Adaptation for Sparse Linear Regression Jonathan Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi

NeurIPS 2023 Provable Benefits of Score Matching Chirag Pabbaraju, Dhruv Rohatgi, Anish Prasad Sevekari, Holden Lee, Ankur Moitra, Andrej Risteski

ICMLW 2023 Provable Benefits of Score Matching Chirag Pabbaraju, Dhruv Rohatgi, Anish Sevekari, Holden Lee, Ankur Moitra, Andrej Risteski

ICLR 2023 Provably Auditing Ordinary Least Squares in Low Dimensions Ankur Moitra, Dhruv Rohatgi

NeurIPS 2022 Learning in Observable POMDPs, Without Computationally Intractable Oracles Noah Golowich, Ankur Moitra, Dhruv Rohatgi

NeurIPS 2022 Lower Bounds on Randomly Preconditioned Lasso via Robust Sparse Designs Jonathan Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi

NeurIPS 2022 Robust Generalized Method of Moments: A Finite Sample Viewpoint Dhruv Rohatgi, Vasilis Syrgkanis

NeurIPS 2020 Constant-Expansion Suffices for Compressed Sensing with Generative Priors Constantinos Daskalakis, Dhruv Rohatgi, Emmanouil Zampetakis

NeurIPS 2020 Truncated Linear Regression in High Dimensions Constantinos Daskalakis, Dhruv Rohatgi, Emmanouil Zampetakis