Combinatorial Causal Bandits without Graph Skeleton

Shi Feng, Nuoya Xiong, Wei Chen

Keywords: Causal Bandits, Online Learning, Multi-armed Bandits, Causal Inference

Verify Author List: I have double-checked the author list and understand that additions and removals will not be allowed after the submission deadline.

TL;DR: We propose two algorithms for the problem "Combinatorial Causal Bandits without Graph Skeleton" and provide a theoretical regret analysis.

Abstract: In combinatorial causal bandits (CCB), the learning agent chooses a subset of variables in each round to intervene and collects feedback from the observed variables to minimize expected regret or sample complexity. Previous works study this problem in both general causal models and binary generalized linear models (BGLMs). However, all of them require prior knowledge of causal graph structure or unrealistic assumptions. This paper studies the CCB problem without the graph structure on binary general causal models and BGLMs. We first provide an exponential lower bound of cumulative regrets for the CCB problem on general causal models. To overcome the exponentially large space of parameters, we then consider the CCB problem on BGLMs. We design a regret minimization algorithm for BGLMs even without the graph skeleton and show that it still achieves $O(\sqrt{T}\ln T)$ expected regret, as long as the causal graph satisfies a weight gap assumption. This asymptotic regret is the same as the state-of-art algorithms relying on the graph structure. Moreover, we propose another algorithm with $O(T^{\frac{2}{3}}\ln T)$ regret to remove the weight gap assumption.

Primary Area: Theory (bandits, computational learning theory, game theory, optimization, statistical learning theory, etc.)

Paper Checklist Guidelines: I certify that all co-authors of this work have read and commit to adhering to the guidelines in Call for Papers.

Student Author: Yes

Submission Number: 97