paper-with-me

홈 › Papers

Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms

2024-08-30 · Ahmed Ben Yahmed, Clément Calauzènes, Vianney Perchet

In the strategic multi-armed bandit setting, when arms possess perfect information about the player's behavior, they can establish an equilibrium where: 1. they retain almost all of their value, 2. they leave the player with a substantial (linear) regret. This study illustrates that, even if complete information is not publicly available to all arms but is shared among them, it is possible to achieve a similar equilibrium. The primary challenge lies in designing a communication protocol that incentivizes the arms to communicate truthfully.

📄 PDF Abstract BibTeX arXiv:2408.17101

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Auction-Based Combinatorial Multi-Armed Bandit Mechanisms with Strategic Arms

2021-05-10 · IEEE Conference on Computer Communications 2021 5 · Guoju Gao, He Huang, Mingjun Xiao, Jie Wu 외

The multi-armed bandit (MAB) model has been deeply studied to solve many online learning problems, such as rate allocation in communication networks, Ad recommendation in social networks, etc. In an MAB model, given N ar…

Computational Efficiency

Multi-armed Bandit Problems with Strategic Arms

2017-06-27 · Mark Braverman, Jieming Mao, Jon Schneider, S. Matthew Weinberg

We study a strategic version of the multi-armed bandit problem, where each arm is an individual strategic agent and we, the principal, pull one arm each round. When pulled, the arm receives some private reward $v_a$ and …

Speculative MoE: Communication Efficient Parallel MoE Inference with Speculative Token and Expert Pre-scheduling

2025-03-06 · Yan Li, Pengfei Zheng, Shuang Chen, Zewei Xu 외

MoE (Mixture of Experts) prevails as a neural architecture that can scale modern transformer-based LLMs (Large Language Models) to unprecedented scales. Nevertheless, large MoEs' great demands of computing power, memory …

Mixture-of-ExpertsScheduling

Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting

2025-01-27 · Ahmed Ben Yahmed, Clément Calauzènes, Vianney Perchet

We consider the classical multi-armed bandit problem, but with strategic arms. In this context, each arm is characterized by a bounded support reward distribution and strategically aims to maximize its own utility by pot…

Communication Enhances LLMs' Stability in Strategic Thinking

2026-02-04 · Nunzio Lore, Babak Heydari arxiv

Large Language Models (LLMs) often exhibit pronounced context-dependent variability that undermines predictable multi-agent behavior in tasks requiring strategic thinking. Focusing on models that range from 7 to 9 billio…