Timezone: »

 
Poster
Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms
Xutong Liu · Jinhang Zuo · Siwei Wang · Carlee Joe-Wong · John C.S. Lui · Wei Chen

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #537
in Poster Session 6 »
In this paper, we study the combinatorial semi-bandits (CMAB) and focus on reducing the dependency of the batch-size $K$ in the regret bound, where $K$ is the total number of arms that can be pulled or triggered in each round. First, for the setting of CMAB with probabilistically triggered arms (CMAB-T), we discover a novel (directional) triggering probability and variance modulated (TPVM) condition that can replace the previously-used smoothness condition for various applications, such as cascading bandits, online network exploration and online influence maximization. Under this new condition, we propose a BCUCB-T algorithm with variance-aware confidence intervals and conduct regret analysis which reduces the $O(K)$ factor to $O(\log K)$ or $O(\log^2 K)$ in the regret bound, significantly improving the regret bounds for the above applications. Second, for the setting of non-triggering CMAB with independent arms, we propose a SESCB algorithm which leverages on the non-triggering version of the TPVM condition and completely removes the dependency on $K$ in the leading regret. As a valuable by-product, the regret analysis used in this paper can improve several existing results by a factor of $O(\log K)$. Finally, experimental evaluations show our superior performance compared with benchmark algorithms in different applications.
Keywords: Triggering arms · Variance-aware · Combinatorial multi-armed bandits · Batch-size
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Xutong Liu (The Chinese University of Hong Kong)
Jinhang Zuo (University of Massachusetts at Amherst)
Siwei Wang (IIIS, Tsinghua University)
Carlee Joe-Wong (Carnegie Mellon University)
John C.S. Lui (Chinese University of Hong Kong)
Wei Chen (Microsoft Research)

More from the Same Authors