AI Paper Atlas

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

On Limited-Memory Subsampling Strategies for Bandits

Dorian Baudry, Yoan Russac, Olivier Cappé

ICML 2021 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms · 1 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 deterministic last-block subsampling for duelsLB-SDA · Stationary one-parameter exponential-family banditsregret: \cR(T) \leq \sum_{k: \mu_k < \mu^\star} \frac{1+\epsilon}{\kl(\mu_k, \mu^\star)} \log(T) + C(\nu, \epsilon)Improved
Limit stored observations per arm using m_r with m_r/\log(r) \to \infty (ablation)LB-SDA · Stationary one-parameter exponential-family banditsregret: \cR_T \leq \sum_{k: \mu_k < \mu^\star} \frac{1+\epsilon}{\kl(\mu_k, \mu^\star)} \log(T) + C'(\nu, \epsilon, \cM)No clear effect
Limit memory to m_r = \log(r)^2 + 50 (ablation)LB-SDA · Stationary Bernoulli bandit, K=2, T=10000regretHurt
Use SW-LB-SDA instead of competing methodsAbruptly changing Bernoulli bandit · Bernoulli instance with three armsregretImproved
Use SW-LB-SDA instead of competing methodsAbruptly changing Gaussian bandit · Gaussian instance with three arms and fixed standard deviationregretImproved
Use SW-LB-SDA without supplying variance informationNon-stationary bandit algorithms · Gaussian bandit with changing standard errorsregretImproved

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