Research map / Bandits and online learning / Online convex optimization and games
Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits
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 |
|---|---|---|---|
| Replace quadratic-in-d analysis with fine-grained FTRL regret decomposition (sub-Gaussian noise) | FTRL for stochastic online linear regression · stochastic online linear regression | regret order in d | Helped |
| Extend analysis from sub-Gaussian to Bernstein noise (bounded by R, variance σ^2) | FTRL · stochastic online regression | regret bound form | No clear effect |
| Variance-aware layered FTRL (MOR-UCB) for heteroscedastic generalized linear bandits | generalized linear bandits with heteroscedastic noise · heteroscedastic bandits | regret order | Helped |
Closest papers by meaning
- Stochastic Online Instrumental Variable Regression: Regrets for Endogeneity and Bandit Feedback (AAAI 2025 · similarity 0.88)
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · similarity 0.88)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.87)
- Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update (ICML 2025 · similarity 0.87)
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.87)
- Improved Online Confidence Bounds for Multinomial Logistic Bandits (ICML 2025 · 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.