LGAIFeb 25, 2021

Combinatorial Bandits under Strategic Manipulations

arXiv:2102.12722v410 citations
AI Analysis

This addresses robustness in sequential learning for applications like recommendations and crowdsourcing, but it is incremental as it relaxes prior adversarial settings.

The paper tackles the problem of combinatorial multi-armed bandits under strategic manipulations, where arms can modify reward signals, and proposes a strategic variant of the combinatorial UCB algorithm that achieves a regret bound of O(m log T + m B_max).

Strategic behavior against sequential learning methods, such as "click framing" in real recommendation systems, have been widely observed. Motivated by such behavior we study the problem of combinatorial multi-armed bandits (CMAB) under strategic manipulations of rewards, where each arm can modify the emitted reward signals for its own interest. This characterization of the adversarial behavior is a relaxation of previously well-studied settings such as adversarial attacks and adversarial corruption. We propose a strategic variant of the combinatorial UCB algorithm, which has a regret of at most $O(m\log T + m B_{max})$ under strategic manipulations, where $T$ is the time horizon, $m$ is the number of arms, and $B_{max}$ is the maximum budget of an arm. We provide lower bounds on the budget for arms to incur certain regret of the bandit algorithm. Extensive experiments on online worker selection for crowdsourcing systems, online influence maximization and online recommendations with both synthetic and real datasets corroborate our theoretical findings on robustness and regret bounds, in a variety of regimes of manipulation budgets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes