Timezone: »
Stochastic high dimensional bandit problems with low dimensional structures are useful in different applications such as online advertising and drug discovery. In this work, we propose a simple unified algorithm for such problems and present a general analysis framework for the regret upper bound of our algorithm. We show that under some mild unified assumptions, our algorithm can be applied to different high-dimensional bandit problems. Our framework utilizes the low dimensional structure to guide the parameter estimation in the problem, therefore our algorithm achieves the comparable regret bounds in the LASSO bandit as a sanity check, as well as novel bounds that depend logarithmically on dimensions in the low-rank matrix bandit, the group sparse matrix bandit, and in a new problem: the multi-agent LASSO bandit.
Author Information
Wenjie Li (Purdue University)
Adarsh Barik (Purdue University)
Jean Honorio (Purdue University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: A Simple Unified Framework for High Dimensional Bandit Problems »
Thu. Jul 21st through Fri the 22nd Room Hall E #1115
More from the Same Authors
-
2023 Poster: Exact Inference in High-order Structured Prediction »
Chuyang Ke · Jean Honorio -
2022 Poster: Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation »
Adarsh Barik · Jean Honorio -
2022 Spotlight: Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation »
Adarsh Barik · Jean Honorio -
2021 Poster: Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation »
Qian Zhang · Yilin Zheng · Jean Honorio -
2021 Poster: A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning »
Abi Komanduru · Jean Honorio -
2021 Spotlight: A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning »
Abi Komanduru · Jean Honorio -
2021 Spotlight: Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation »
Qian Zhang · Yilin Zheng · Jean Honorio -
2019 Poster: Optimality Implies Kernel Sum Classifiers are Statistically Efficient »
Raphael Meyer · Jean Honorio -
2019 Oral: Optimality Implies Kernel Sum Classifiers are Statistically Efficient »
Raphael Meyer · Jean Honorio -
2018 Poster: Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time »
Asish Ghoshal · Jean Honorio -
2018 Oral: Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time »
Asish Ghoshal · Jean Honorio