Making the last iterate of sgd information theoretically optimal P Jain, D Nagaraj, P Netrapalli Conference on Learning Theory, 1752-1755, 2019 | 91 | 2019 |

SGD without Replacement: Sharper Rates for General Smooth Convex Functions D Nagaraj, P Jain, P Netrapalli International Conference on Machine Learning, 4703-4711, 2019 | 81* | 2019 |

A law of robustness for two-layers neural networks S Bubeck, Y Li, DM Nagaraj Conference on Learning Theory, 804-820, 2021 | 55 | 2021 |

Least squares regression with markovian data: Fundamental limits and algorithms D Nagaraj, X Wu, G Bresler, P Jain, P Netrapalli Advances in neural information processing systems 33, 16666-16676, 2020 | 55 | 2020 |

The staircase property: How hierarchical structure can guide deep learning E Abbe, E Boix-Adsera, MS Brennan, G Bresler, D Nagaraj Advances in Neural Information Processing Systems 34, 26989-27002, 2021 | 44 | 2021 |

Phase transitions for detecting latent geometry in random graphs M Brennan, G Bresler, D Nagaraj Probability Theory and Related Fields 178 (3), 1215-1289, 2020 | 36 | 2020 |

Optimal Single Sample Tests for Structured versus Unstructured Network Data G Bresler, D Nagaraj arXiv preprint arXiv:1802.06186, 2018 | 30 | 2018 |

Stein’s method for stationary distributions of Markov chains and application to Ising models G Bresler, D Nagaraj | 29 | 2019 |

Near-optimal offline and streaming algorithms for learning non-linear dynamical systems S Kowshik, D Nagaraj, P Jain, P Netrapalli Advances in Neural Information Processing Systems 34, 8518-8531, 2021 | 28 | 2021 |

Online target q-learning with reverse experience replay: Efficiently finding the optimal policy for linear mdps N Agarwal, S Chaudhuri, P Jain, D Nagaraj, P Netrapalli arXiv preprint arXiv:2110.08440, 2021 | 23 | 2021 |

Sharp representation theorems for relu networks with precise dependence on depth G Bresler, D Nagaraj Advances in Neural Information Processing Systems 33, 10697-10706, 2020 | 22 | 2020 |

Streaming linear system identification with reverse experience replay S Kowshik, D Nagaraj, P Jain, P Netrapalli Advances in Neural Information Processing Systems 34, 30140-30152, 2021 | 21* | 2021 |

Continuous limit of discrete quantum walks D MN, TA Brun Physical Review A 91 (6), 062304, 2015 | 21 | 2015 |

A corrective view of neural networks: Representation, memorization and learning G Bresler, D Nagaraj Conference on Learning Theory, 848-901, 2020 | 18 | 2020 |

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularization D Nagaraj, D Precup, G Patil, LA Prashanth | 10* | 2023 |

Stochastic re-weighted gradient descent via distributionally robust optimization R Kumar, K Majmundar, D Nagaraj, AS Suggala arXiv preprint arXiv:2306.09222, 2023 | 8* | 2023 |

Provably fast finite particle variants of SVGD via virtual particle stochastic approximation A Das, D Nagaraj Advances in Neural Information Processing Systems 36, 2024 | 5 | 2024 |

Indexability is not enough for whittle: Improved, near-optimal algorithms for restless bandits A Ghosh, D Nagaraj, M Jain, M Tambe arXiv preprint arXiv:2211.00112, 2022 | 4 | 2022 |

Utilising the clt structure in stochastic gradient based sampling: Improved analysis and faster algorithms A Das, DM Nagaraj, A Raj The Thirty Sixth Annual Conference on Learning Theory, 4072-4129, 2023 | 3 | 2023 |

Open Problem: Do Good Algorithms Necessarily Query Bad Points? R Ge, P Jain, SM Kakade, R Kidambi, DM Nagaraj, P Netrapalli Conference on Learning Theory, 3190-3193, 2019 | 3 | 2019 |