Near-Optimal Collaborative Learning in Bandits
Nov 28, 2022
Speakers
Clémence Réda
Speaker · 0 followers
Sattar Vakili
Speaker · 0 followers
Emilie Kaufmann
Speaker · 0 followers
About
This paper introduces a general multi-agent bandit model in which each agent is facing a finite set of arms and may communicate with other agents through a central controller in order to identify -in pure exploration- or play -in regret minimization- its optimal arm. The twist is that the optimal arm for each agent is the arm with largest expected mixed reward, where the mixed reward of an arm is a weighted sum of the rewards of this arm for all agents. This makes communication between agents often necessary. This general setting allows to recover and extend several recent models for collaborative bandit learning, including the recently proposed federated learning with personalization [Shi et al., 2021]. In this paper, we provide new lower bounds on the sample complexity of pure exploration and on the regret. We then propose a near-optimal algorithm for pure exploration. This algorithm is based on phased elimination with two novel ingredients: a data-dependent sampling scheme within each phase, aimed at matching a relaxation of the lower bound.This paper introduces a general multi-agent bandit model in which each agent is facing a finite set of arms and may communicate with other agents through a central controller in order to identify -in pure exploration- or play -in regret minimization- its optimal arm. The twist is that the optimal arm for each agent is the arm with largest expected mixed reward, where the mixed reward of an arm is a weighted sum of the rewards of this arm for all agents. This makes communication between agents of…
Organizer
NeurIPS 2022
Account · 966 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
LION: Latent Point Diffusion Models for 3D Shape Generation
Watch later
Xiaohui Zeng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Unified Framework for Deep Symbolic Regression
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Train Offline, Test Online: A Real Robot Learning Benchmark
Watch later
Gaoyue Zhou, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Human-AI Interaction in Selective Prediction Systems
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Online Allocation and Learning in the Presence of Strategic Agents
Watch later
Steven Yin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
DRL-EPANET: Deep reinforcement learning for optimal control at scale in Water Distribution Systems
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%