Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use IS-weighted ERM instead of unweighted ERM | Linear regression and LASSO on contextual-bandit-collected data · 51 OpenML-CC18 datasets | mean-squared error | Helped |
| Use different weighting schemes instead of ISWERM | CART regression on contextual-bandit-collected data · 51 OpenML-CC18 datasets | mean-squared error | No clear effect |
| Apply an IS-structure-aware maximal inequality rather than a generic inequality for weighted sequential processes | IS-weighted ERM with adaptively collected data · Adaptive data with decaying exploration | excess-risk convergence rate: O((γ^avg_T/T)^{1/p∧1/2}) | Helped |
| Use ISWERM for policy learning under epsilon-greedy exploration with ε_t=t^{-β} | Policy learning · Contextual-bandit-collected data | expected regret: O(T^{-(1-β)/2}) | Helped |
Closest papers by meaning
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.88)
- Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning (NeurIPS 2024 · similarity 0.88)
- Sample-Optimal Agnostic Boosting with Unlabeled Data (ICML 2025 · similarity 0.88)
- On the Asymptotic Distribution of the Minimum Empirical Risk (ICML 2024 · similarity 0.87)
- Boosting Test Performance with Importance Sampling--a Subpopulation Perspective (AAAI 2025 · similarity 0.87)
- Universal Rates of Empirical Risk Minimization (NeurIPS 2024 · similarity 0.87)
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.