AI Paper Atlas

Research map / Bandits and online learning / Contextual bandits and Thompson sampling

Reward Imputation with Sketching for Contextual Batched Bandits

Xiao Zhang, Ninglu Shao, Zihua Si, Jun Xu, Wenhan Wang, Hanjing Su, Ji-Rong Wen

NeurIPS 2023 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Practical contextual bandit extensions · 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
reward imputation (SPUIR) vs second-best baselinecontextual batched bandit policy · commercial productCVR: 1.07%Improved
reward imputation (SPUIR) vs second-best baselinecontextual batched bandit policy · commercial productCTCVR: 1.12%Improved
add reward imputation to batched bandit (PUIR vs SBUCB)SBUCB · commercial productCVR: 0.8569 -> 0.8807Improved
use sketching in reward imputation (SPUIR vs PUIR)PUIR · commercial producttime (sec): 184.3575 -> 81.5753Improved
use sketching in reward imputation (SPUIR vs PUIR)PUIR · commercial productCVR: 0.8807 -> 0.8770No clear effect
add rate scheduling to sketched imputation (SPUIR-RS vs SPUIR)SPUIR · commercial productCVR: 0.8770 -> 0.8758No clear effect
add rate scheduling to non-sketched imputation (PUIR-RS vs PUIR)PUIR · commercial productCTCVR: 0.4411 -> 0.4389No clear effect
sketched imputation vs DFM-S baseline runtimeSPUIR · commercial producttime (sec): 302.3140 -> 81.5753Improved
sketched imputation vs BLTS-B baseline runtimeSPUIR · commercial producttime (sec): 218.2109 -> 81.5753Improved
sketching cost versus no-imputation baselinesSPUIR · commercial producttime (sec): 43.5435 -> 81.5753Hurt
use nonlinear kernel reward model (SPUIR-Kernel)SPUIR · synthetic datasetaverage rewardImproved
batch size B set to 1,000 (C_B = 25) versus other sizes (ablation)SPUIR · Criteo-recentaverage rewardImproved

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