| 2026 | COLT | Steering diffusion models with quadratic rewards: a fine-grained analysis. | Ankur Moitra, Andrej Risteski, Dhruv Rohatgi |
| 2025 | COLT | 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 |
| 2025 | COLT | 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 |
| 2025 | COLT | Necessary and Sufficient Oracles: Toward a Computational Taxonomy for Reinforcement Learning. | Dhruv Rohatgi, Dylan J. Foster |
| 2025 | ICLR | 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 |
| 2025 | ICML | Towards characterizing the value of edge embeddings in Graph Neural Networks. | Dhruv Rohatgi, Tanya Marwah, Zachary Chase Lipton, Jianfeng Lu, Ankur Moitra, Andrej Risteski |
| 2024 | COLT | Lasso with Latents: Efficient Estimation, Covariate Rescaling, and Computational-Statistical Gaps. | Jonathan A. Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi |
| 2024 | FOCS | Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning. | Noah Golowich, Ankur Moitra, Dhruv Rohatgi |
| 2024 | STOC | Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles. | Noah Golowich, Ankur Moitra, Dhruv Rohatgi |
| 2023 | ICLR | Provably Auditing Ordinary Least Squares in Low Dimensions. | Ankur Moitra, Dhruv Rohatgi |
| 2023 | STOC | Planning and Learning in Partially Observable Systems via Filter Stability. | Noah Golowich, Ankur Moitra, Dhruv Rohatgi |
| 2021 | FOCS | On the Power of Preconditioning in Sparse Linear Regression. | Jonathan A. Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi |
| 2020 | SODA | Near-Optimal Bounds for Online Caching with Machine Learned Advice. | Dhruv Rohatgi |