AI Paper Atlas

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

Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward

Lixing Chen, Jie Xu, Zhuo Lu

NeurIPS 2018 · Bandits and online learning › Multi-armed bandits · approach: Non-stationary and structured-reward bandits

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
make the selection submodularity-aware (CC-MAB vs CC-MAB-NS) (ablation)CC-MAB · Yelp crowdsourcingcumulative reward: 0.0% -> 17.1%Improved
set p=1 so reward is non-submodular (ablation)CC-MAB vs CC-MAB-NS · Yelp crowdsourcing, Dixit-Stiglitz rewardcumulative reward: 0.0%No clear effect
increase submodularity strength p above 1CC-MAB-NS · Yelp crowdsourcingcumulative reward loss vs CC-MAB: 0.0% -> 17.1%Hurt
use context information of arms (CC-MAB, k-LinUCB, CC-MAB-NS vs UCB, Random)bandit selection · Yelp crowdsourcingcumulative rewardImproved
increase budget B from 10 toward 100all algorithms · Yelp crowdsourcing, 200 roundscumulative rewardImproved
submodularity-aware selection saturates earlier in budgetOracle and CC-MAB · Yelp crowdsourcing, 200 roundsbudget at saturation: B = 50 vs B = 90Improved
increase budget BCC-MAB · Yelp crowdsourcingregretImproved
compare CC-MAB to Oracle at all budgetsCC-MAB · Yelp crowdsourcingcumulative rewardNo clear effect

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