 Experimental Design for Semiparametric BanditsAnnual Conference Computational Learning Theory (COLT), 2025 |
 On the Problem of Best Arm RetentionTheoretical Computer Science (TCS), 2025 |
 Sequential Learning of the Pareto Front for Multi-objective BanditsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 |
 Enhancing Preference-based Linear Bandits via Human Response TimeNeural Information Processing Systems (NeurIPS), 2024 |
 Regret Minimization via Saddle Point OptimizationNeural Information Processing Systems (NeurIPS), 2024 |
 LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding
Linear Bandit ProblemPacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2024 |
 |
 Experiment Planning with Function ApproximationNeural Information Processing Systems (NeurIPS), 2024 |
 Optimal Batched Best Arm IdentificationNeural Information Processing Systems (NeurIPS), 2023 |
 Pure Exploration in Asynchronous Federated BanditsConference on Uncertainty in Artificial Intelligence (UAI), 2023 |
 Optimal Exploration is no harder than Thompson SamplingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Experimental Designs for Heteroskedastic VarianceNeural Information Processing Systems (NeurIPS), 2023 |
 A/B Testing and Best-arm Identification for Linear Bandits with
Robustness to Non-stationarityInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
 Pure Exploration in Bandits with Linear ConstraintsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Emil Carlsson Debabrota Basu Fredrik D. Johansson Devdatt Dubhashi |
 Cooperative Thresholded Lasso for Sparse Linear BanditEuropean Conference on Artificial Intelligence (ECAI), 2023 |
 Multi-task Representation Learning for Pure Exploration in Linear
BanditsInternational Conference on Machine Learning (ICML), 2023 |
 Best Arm Identification in Stochastic Bandits: Beyond optimalityIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2023 |
 Scalable Representation Learning in Linear Contextual Bandits with
Constant Regret GuaranteesNeural Information Processing Systems (NeurIPS), 2022 |
 SPRT-based Efficient Best Arm Identification in Stochastic BanditsIEEE Journal on Selected Areas in Information Theory (JSAIT), 2022 |
 Instance-optimal PAC Algorithms for Contextual BanditsNeural Information Processing Systems (NeurIPS), 2022 |
 Active Learning with Safety ConstraintsNeural Information Processing Systems (NeurIPS), 2022 |
 On Elimination Strategies for Bandit Fixed-Confidence IdentificationNeural Information Processing Systems (NeurIPS), 2022 |
 Instance-Dependent Regret Analysis of Kernelized BanditsInternational Conference on Machine Learning (ICML), 2022 |
 Nearly Optimal Algorithms for Level Set EstimationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Dealing With Misspecification In Fixed-Confidence Linear Top-m
IdentificationNeural Information Processing Systems (NeurIPS), 2021 |
 Vector Optimization with Stochastic Bandit FeedbackInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 |
 Design of Experiments for Stochastic Contextual Linear BanditsNeural Information Processing Systems (NeurIPS), 2021 |
 Pure Exploration in Kernel and Neural BanditsNeural Information Processing Systems (NeurIPS), 2021 |
 Fixed-Budget Best-Arm Identification in Structured BanditsInternational Joint Conference on Artificial Intelligence (IJCAI), 2021 |
 Minimax Optimal Fixed-Budget Best Arm Identification in Linear BanditsNeural Information Processing Systems (NeurIPS), 2021 Junwen Yang Vincent Y. F. Tan |
 High-Dimensional Experimental Design and Kernel BanditsInternational Conference on Machine Learning (ICML), 2021 |
