Subhojyoti Mukherjee

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 25

Top Topics

Multi Armed Bandit

Transductive Inference

Multiphase Segmentation

Policy Evaluation

Top Venues

IEEE J. Sel. Areas Inf. Theory

Publications

Subhojyoti Mukherjee, Josiah P. Hanna, Qiaomin Xie, Robert D. Nowak
Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning. CoRR (2024)
Aniruddha Bhargava, Lalit Jain, Branislav Kveton, Ge Liu, Subhojyoti Mukherjee
Off-Policy Evaluation from Logged Human Feedback. CoRR (2024)
Subhojyoti Mukherjee, Qiaomin Xie, Josiah P. Hanna, Robert D. Nowak
SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits. AISTATS (2024)
Subhojyoti Mukherjee, Josiah P. Hanna, Robert D. Nowak
SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP. CoRR (2024)
Subhojyoti Mukherjee, Ge Liu, Aniket Deshmukh, Anusha Lalitha, Yifei Ma, Branislav Kveton
Experimental Design for Active Transductive Inference in Large Language Models. CoRR (2024)
Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari, Aniket Deshmukh, Ge Liu, Yifei Ma, Branislav Kveton
Optimal Design for Human Feedback. CoRR (2024)
Subhojyoti Mukherjee, Qiaomin Xie, Josiah Hanna, Robert D. Nowak
Multi-task Representation Learning for Pure Exploration in Bilinear Bandits. NeurIPS (2023)
Subhojyoti Mukherjee, Qiaomin Xie, Josiah P. Hanna, Robert D. Nowak
Multi-task Representation Learning for Pure Exploration in Bilinear Bandits. CoRR (2023)
Subhojyoti Mukherjee, Ruihao Zhu, Branislav Kveton
Efficient and Interpretable Bandit Algorithms. CoRR (2023)
Subhojyoti Mukherjee, Qiaomin Xie, Josiah Hanna, Robert D. Nowak
SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits. CoRR (2023)
Blake Mason, Lalit Jain, Subhojyoti Mukherjee, Romain Camilleri, Kevin G. Jamieson, Robert D. Nowak
Nearly Optimal Algorithms for Level Set Estimation. AISTATS (2022)
Subhojyoti Mukherjee, Ardhendu S. Tripathy, Robert D. Nowak
Chernoff Sampling for Active Testing and Extension to Active Regression. AISTATS (2022)
Subhojyoti Mukherjee
Safety aware changepoint detection for piecewise i.i.d. bandits. UAI (2022)
Subhojyoti Mukherjee, Josiah P. Hanna, Robert D. Nowak
ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling. CoRR (2022)
Subhojyoti Mukherjee, Josiah P. Hanna, Robert D. Nowak
ReVar: Strengthening policy evaluation via reduced variance sampling. UAI (2022)
Subhojyoti Mukherjee
Safety Aware Changepoint Detection for Piecewise i.i.d. Bandits. CoRR (2022)
Samarth Gupta, Shreyas Chaudhari, Subhojyoti Mukherjee, Gauri Joshi, Osman Yagan
A Unified Approach to Translate Classical Bandit Algorithms to Structured Bandits. ICASSP (2021)
Blake Mason, Romain Camilleri, Subhojyoti Mukherjee, Kevin Jamieson, Robert D. Nowak, Lalit Jain
Nearly Optimal Algorithms for Level Set Estimation. CoRR (2021)
Samarth Gupta, Shreyas Chaudhari, Subhojyoti Mukherjee, Gauri Joshi, Osman Yagan
A Unified Approach to Translate Classical Bandit Algorithms to the Structured Bandit Setting. IEEE J. Sel. Areas Inf. Theory 1 (3) (2020)
Subhojyoti Mukherjee, Ardhendu Tripathy, Robert D. Nowak
Generalized Chernoff Sampling for Active Learning and Structured Bandit Algorithms. CoRR (2020)
Subhojyoti Mukherjee, Odalric-Ambrym Maillard
Distribution-dependent and Time-uniform Bounds for Piecewise i.i.d Bandits. CoRR (2019)
Subhojyoti Mukherjee, K. P. Naveen, Nandan Sudarsanam, Balaraman Ravindran
Efficient-UCBV: An Almost Optimal Algorithm Using Variance Estimates. AAAI (2018)
Subhojyoti Mukherjee, Kolar Purushothama Naveen, Nandan Sudarsanam, Balaraman Ravindran
Thresholding Bandits with Augmented UCB. IJCAI (2017)
Subhojyoti Mukherjee, K. P. Naveen, Nandan Sudarsanam, Balaraman Ravindran
Efficient-UCBV: An Almost Optimal Algorithm using Variance Estimates. CoRR (2017)
Subhojyoti Mukherjee, Kolar Purushothama Naveen, Nandan Sudarsanam, Balaraman Ravindran
Thresholding Bandits with Augmented UCB. CoRR (2017)