Collaborative Top Distribution Identifications with Limited Interaction
Offered By: IEEE via YouTube
Course Description
Overview
Explore a 25-minute IEEE conference talk on collaborative learning strategies for Multi-Armed Bandits (MAB) problems, focusing on top-m distribution identifications with limited interaction. Delve into the intricacies of the Top-m problem in MAB, examining the collaborative learning approach and its algorithm. Understand the key differences between Top-1 and Top-m scenarios, and learn about the reduction technique and error amplification in this context. Presented by Nikolai Karpov, Qin Zhang, and Yuan Zhou from Indiana University at Bloomington and the University of Illinois at Urbana-Champaign, this talk provides valuable insights into advanced MAB problem-solving techniques.
Syllabus
Intro
Top-m problem in Multi-Armed Bandits (MAB)
Collaborative Learning for MAB
Algorithm
Difference between Top-1 and Top-m Top-m
Reduction
Error amplification
Taught by
IEEE FOCS: Foundations of Computer Science
Tags
Related Courses
An Improved Exponential-Time Approximation Algorithm for Fully-Alternating Games Against NatureIEEE via YouTube Computation in the Brain Tutorial - Part 2
IEEE via YouTube Computation in the Brain - Part 1
IEEE via YouTube Spectral Independence in High-Dimensional Expanders and Applications to the Hardcore Model
IEEE via YouTube Cookbook Lower Bounds for Statistical Inference in Distributed and Constrained Settings - Part 1
IEEE via YouTube