AI Paper Atlas

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

PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits

Kyoungseok Jang, Chicheng Zhang, Kwang-Sung Jun

NeurIPS 2022 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Linear and generalized linear bandits · 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 PopArt with the H_*^2-optimal sampling design instead of C_min-Lasso with its designSparse linear regression · Sparse linear regression, both reported casesℓ1 estimation errorImproved
Use the PopArt-optimal sampling design with Lasso instead of the C_min-optimal designLasso · Sparse linear regression, hard instance where H_*^2 ≪ C_min^{-1}ℓ1 estimation errorImproved
Use PopArt rather than Lasso on the same data points and designSparse linear regression · Sparse linear regression, both reported casesℓ1 estimation errorImproved
Use the PopArt-based bandit algorithm with wPopArt instead of ESTCSparse linear bandits · Hard instance and general unit vectorscumulative regretImproved
Use the H_*^2 experimental-design objective rather than the C_min design objectivePopArt-based sparse linear bandits · Sparse linear bandits, data-poor regimeregret upper bound: H_*^2 ≤ C_min^{-1} ≤ d H_*^2Improved
Warm up with a coarse estimate and use it as PopArt's pilot estimatorwPopArt · Sparse linear estimationℓ1 estimation error bound: 8 s σ √(H^2(Q(μ)) ln(2d/δ)/n_0)Improved

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