AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Maximizing and Satisficing in Multi-armed Bandits with Graph Information

Parth Kashyap Thaker, Mohit Malu, Nikhil Rao, Gautam Dasarathy

NeurIPS 2022 · Bandits and online learning › Multi-armed bandits · approach: Non-stationary and structured-reward bandits · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use graph side information (GRUB with MVM) instead of UCBUCB · Github Social and LastFMrounds to find best arm: 4500 -> 300Improved
use graph-based sampling policies instead of cyclic UCBUCB · synthetic SBM and BA graphsstopping timeImproved
increase number of arms with fixed 10 clustersGRUB-MVM/JVM-N/JVM-O · synthetic SBM and BA graphsstopping timeImproved
increase number of arms with fixed 10 clusterscyclic UCB · synthetic SBM and BA graphsstopping timeHurt
use MVM sampling policy versus other graph-based policiesGRUB · Github and LastFMarms remaining over timeImproved
use cyclic sampling inside GRUBGRUB · real-world graphsarms remaining over timeHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy