Research map / Bandits and online learning / Online convex optimization and games
Online PAC-Bayes Learning
Maxime Haddouche, Benjamin Guedj
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use OPB with Gaussian prior instead of OGD | OPB (Gibbs Gauss) · Breast Cancer, Pima, Boston Housing | average cumulative loss | Improved |
| Use Laplace prior instead of Gaussian prior in OPB (ablation) | OPB (Gibbs Laplace) · all four datasets | average cumulative loss | Hurt |
| Use OPB instead of SVB | OPB · Boston Housing | average cumulative loss | Hurt |
| Use OPBD instead of OGD | OPBD · classification datasets | average cumulative loss | Improved |
| Use OPBD instead of SVB | OPBD · regression datasets | average cumulative loss | No clear effect |
| Use Psi_2 instead of Psi_1 in OPBD (ablation) | OPBD · California Housing | average cumulative loss | Improved |
| Use Psi_1 instead of Psi_2 in OPBD (ablation) | OPBD · Boston Housing | average cumulative loss | Improved |
| Use Psi_1 versus Psi_2 in OPBD (ablation) | OPBD · classification tasks | average cumulative loss | No clear effect |
Closest papers by meaning
- PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison (TPAMI 2023 · similarity 0.89)
- Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss (NeurIPS 2024 · similarity 0.88)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.87)
- Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability (ICML 2025 · similarity 0.87)
- Online Set Learning from Precision and Recall Feedback (NeurIPS 2026 · similarity 0.87)
- Online Markov Decision Processes Configuration with Continuous Decision Space (AAAI 2024 · similarity 0.86)
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.
