AI Paper Atlas

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

Communication-Constrained Bandits under Additive Gaussian Noise

Prathamesh Mayekar, Jonathan Scarlett, Vincent Tan

ICML 2023 · Bandits and online learning › Multi-armed bandits · approach: Multi-agent bandits · 0 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 multi-subphase uniform exploration with successively refined reward centering and scalingUE-UCB++ with CAS · Distributed stochastic multi-armed bandit over AWGNregret upper bound: \frac{8 K B \log B}{\mathtt{SNR} \wedge 1}+6KB + 8 \sqrt{\left(\frac{4}{\mathtt{SNR}}+1\right)} \cdot \sqrt{ KT \ln T}Improved
Center each reward using the previous subphase's mean estimate and scale according to its second-moment boundUE-UCB++ · Distributed stochastic multi-armed bandit over AWGNvariance of mean estimatesImproved
Use zero side information rather than sending learned mean estimates (ablation)UCB0 with CAS relative to UE-UCB++ · Distributed stochastic multi-armed bandit over AWGNregret upper bound: 8 \sqrt{ \frac{B^2}{\mathtt{SNR}}+1} \cdot \sqrt{KT \ln T} + 6 KB; \frac{8 K B \log B}{\mathtt{SNR} \wedge 1}+6KB + 8 \sHurt
Use a single uniform-exploration phase instead of the refined multi-subphase scheme (ablation)UE-UCB relative to UE-UCB++ · Distributed stochastic multi-armed bandit over AWGNadditive regret term: \frac{2KB^3}{\mathtt{SNR}}; \frac{8 K B \log B}{\mathtt{SNR} \wedge 1}Hurt
Replace UCB with MOSS in the final phase (ablation)UE-UCB++ · Distributed stochastic multi-armed bandit over AWGNregret upper-bound logarithmic factor: The \ln T factor ... can be removedImproved
Use CAS encoding rather than quantization followed by transmission over AWGNDistributed bandit communication · Distributed stochastic multi-armed bandit over AWGNregretImproved

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