AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Non-stationary Bandits with Knapsacks

Shang Liu, Jiashuo Jiang, Xiaocheng Li

NeurIPS 2022 · Bandits and online learning › Online convex optimization and games · approach: Best-of-both-worlds bandit algorithms · 6 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 naive stationary UCB instead of SW-UCB in the one-dimensional two-armed instanceSW-UCB · Example 1 (d=1)cumulative rewardNo clear effect
use naive stationary UCB instead of SW-UCB in the two-dimensional instanceSW-UCB · Example 2 (d=2)cumulative rewardHurt
use adversarial LagrangeBwK instead of SW-UCBSW-UCB · Examples 1 and 2cumulative rewardHurt
increase W with V fixedSW-UCB and naive UCB · Example 3regretHurt
increase W with V fixedLagrangeBwK · Example 3regretNo clear effect
use SW-UCB instead of LagrangeBwK at small WSW-UCB · Example 3regretImproved
use SW-UCB instead of LagrangeBwK at very large WSW-UCB · Example 3regretHurt
use SW-UCB instead of LagrangeBwK in slowly varying environmentsSW-UCB · Example 4 (fixed W, varying V)regretImproved
increase V (rapidly changing environment)SW-UCB · Example 4regretHurt
rapidly changing environment, SW-UCB versus LagrangeBwKSW-UCB · Example 4regretImproved

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