Timezone: »
Invited Talk 6 - Efficient continuous-action contextual bandits via reduction to extreme multiclass classification - Chicheng Zhang
Chicheng Zhang
Fri Jul 17 12:50 PM -- 01:20 PM (PDT) @
We create a computationally tractable algorithm for contextual bandit learning with one-dimensional continuous actions with unknown structure on the loss functions. In a nutshell, our algorithm, Continuous Action Tree with Smoothing (CATS), reduces continuous-action contextual bandit learning to cost-sensitive extreme multiclass classification, where each class corresponds to a discretized action. We show that CATS admits an online implementation that has low training and test time complexities per example, and enjoys statistical consistency guarantees under certain realizability assumptions. We also verify the efficiency and efficacy of CATS through large-scale experiments.
Author Information
Chicheng Zhang (University of Arizona)
More from the Same Authors
-
2021 : Margin-distancing for safe model explanation »
Tom Yan · Chicheng Zhang -
2021 : Provably Efficient Multi-Task Reinforcement Learning with Model Transfer »
Chicheng Zhang · Zhi Wang -
2022 Poster: Thompson Sampling for Robust Transfer in Multi-Task Bandits »
Zhi Wang · Chicheng Zhang · Kamalika Chaudhuri -
2022 Poster: Active fairness auditing »
Tom Yan · Chicheng Zhang -
2022 Spotlight: Thompson Sampling for Robust Transfer in Multi-Task Bandits »
Zhi Wang · Chicheng Zhang · Kamalika Chaudhuri -
2022 Oral: Active fairness auditing »
Tom Yan · Chicheng Zhang -
2020 : Invited Talk 6 Q&A - Chicheng Zhang »
Chicheng Zhang