Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Barron and Cover’s Theory in Supervised Learning and its Application to Lasso
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 |
|---|---|---|---|
| increase signal-to-noise ratio from 0.5 to 10 | Lasso regret bound · Gaussian random design, n=200, p=1000 | tightness of regret bound: about six times larger than 2d2H when SNR is 10 | Hurt |
| low SNR of 0.5 | Lasso regret bound · Gaussian random design, n=200, p=1000 | tightness of regret bound | Helped |
| compare Bhattacharyya divergence d0.5 with 2 squared Hellinger distance | Lasso · Simulation, 100 trials | loss | No clear effect |
Closest papers by meaning
- Non-Stationary Online Structured Prediction with Surrogate Losses (ICML 2026 · similarity 0.85)
- On the Efficiency of ERM in Feature Learning (NeurIPS 2024 · similarity 0.85)
- A Minimax Approach to Supervised Learning (NeurIPS 2016 · similarity 0.85)
- Tight Risk Bounds for Gradient Descent on Separable Data (NeurIPS 2023 · similarity 0.84)
- Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood (NeurIPS 2024 · similarity 0.84)
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.84)
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.