Koulik Khamaru

33 papers A* 4A 2Journal 27

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Efficient Inference after Directionally Stable Adaptive Experiments. CoRR Zikai Shen, Houssam Zenati, Nathan Kallus, Arthur Gretton, Koulik Khamaru, Aurélien Bibaut
2026	J	`jnl`	Stability and Robustness via Regularization: Bandit Inference via Regularized Stochastic Mirror Descent. CoRR Budhaditya Halder, Ishan Sengupta, Koustav Chowdhury, Koulik Khamaru
2025	J	`jnl`	Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability. CoRR Samya Praharaj, Koulik Khamaru
2025	J	`jnl`	Instability, Computational Efficiency and Statistical Accuracy. J. Mach. Learn. Res. Nhat Ho, Koulik Khamaru, Raaz Dwivedi, Martin J. Wainwright, Michael I. Jordan, Bin Yu
2025	J	`jnl`	On Instability of Minimax Optimal Optimism-Based Bandit Algorithms. CoRR Samya Praharaj, Koulik Khamaru
2025	J	`jnl`	Stable Thompson Sampling: Valid Inference via Variance Inflation. CoRR Budhaditya Halder, Shubhayan Pan, Koulik Khamaru
2024	J	`jnl`	Inference with the Upper Confidence Bound Algorithm. CoRR Koulik Khamaru, Cun-Hui Zhang
2024	J	`jnl`	Stochastic Optimization with Constraints: A Non-asymptotic Instance-Dependent Analysis. CoRR Koulik Khamaru
2024	J	`jnl`	UCB algorithms for multi-armed bandits: Precise regret and adaptive inference. CoRR Qiyang Han, Koulik Khamaru, Cun-Hui Zhang
2023	A*	`conf`	Adaptive Linear Estimating Equations. NeurIPS Mufang Ying, Koulik Khamaru, Cun-Hui Zhang
2023	J	`jnl`	Adaptive Linear Estimating Equations. CoRR Mufang Ying, Koulik Khamaru, Cun-Hui Zhang
2023	J	`jnl`	Instance-Dependent Confidence and Early Stopping for Reinforcement Learning. J. Mach. Learn. Res. Eric Xia, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan
2023	J	`jnl`	Semi-parametric inference based on adaptively collected data. CoRR Licong Lin, Koulik Khamaru, Martin J. Wainwright
2023	A*	`conf`	Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference. NeurIPS Licong Lin, Mufang Ying, Suvrojit Ghosh, Koulik Khamaru, Cun-Hui Zhang
2023	J	`jnl`	Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference. CoRR Licong Lin, Mufang Ying, Suvrojit Ghosh, Koulik Khamaru, Cun-Hui Zhang
2022	J	`jnl`	Instance-Dependent Confidence and Early Stopping for Reinforcement Learning. CoRR Koulik Khamaru, Eric Xia, Martin J. Wainwright, Michael I. Jordan
2022	J	`jnl`	Optimal variance-reduced stochastic approximation in Banach spaces. CoRR Wenlong Mou, Koulik Khamaru, Martin J. Wainwright, Peter L. Bartlett, Michael I. Jordan
2021	J	`jnl`	Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning. CoRR Koulik Khamaru, Eric Xia, Martin J. Wainwright, Michael I. Jordan
2021	J	`jnl`	Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis. SIAM J. Math. Data Sci. Koulik Khamaru, Ashwin Pananjady, Feng Ruan, Martin J. Wainwright, Michael I. Jordan
2021	J	`jnl`	Near-optimal inference in adaptive linear regression. CoRR Koulik Khamaru, Yash Deshpande, Lester Mackey, Martin J. Wainwright
2020	J	`jnl`	Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. J. Mach. Learn. Res. Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
2020	J	`jnl`	Instability, Computational Efficiency and Statistical Accuracy. CoRR Nhat Ho, Koulik Khamaru, Raaz Dwivedi, Martin J. Wainwright, Michael I. Jordan, Bin Yu
2020	J	`jnl`	Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis. CoRR Koulik Khamaru, Ashwin Pananjady, Feng Ruan, Martin J. Wainwright, Michael I. Jordan
2020	A	`conf`	Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models. AISTATS Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan, Bin Yu
2019	J	`jnl`	Challenges with EM in application to weakly identifiable mixture models. CoRR Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan, Bin Yu
2019	J	`jnl`	Computation of the maximum likelihood estimator in low-rank factor analysis. Math. Program. Koulik Khamaru, Rahul Mazumder
2019	J	`jnl`	Convergence Guarantees for a Class of Non-convex and Non-smooth Optimization Problems. J. Mach. Learn. Res. Koulik Khamaru, Martin J. Wainwright
2019	A	`conf`	Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. AISTATS Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
2018	A*	`conf`	Convergence guarantees for a class of non-convex and non-smooth optimization problems. ICML Koulik Khamaru, Martin J. Wainwright
2018	J	`jnl`	Convergence guarantees for a class of non-convex and non-smooth optimization problems. CoRR Koulik Khamaru, Martin J. Wainwright
2018	J	`jnl`	Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems. CoRR Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, Martin J. Wainwright
2018	A*	`conf`	Theoretical guarantees for EM under misspecified Gaussian mixture models. NeurIPS Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Martin J. Wainwright, Michael I. Jordan
2014	J	`jnl`	A Peak Synchronization Measure for Multiple Signals. IEEE Trans. Signal Process. Rahul Biswas, Koulik Khamaru, Kaushik Kumar Majumdar