Research map / Bandits and online learning / Online convex optimization and games
Likelihood Ratio Confidence Sets for Sequential Decision Making
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 likelihood-ratio confidence sets instead of other provably valid confidence sets | UCB with RKHS payoff functions · Gaussian additive-noise bandit | cumulative regret | Helped |
| Use likelihood-ratio confidence sets instead of other provably valid confidence sets | UCB with RKHS payoff functions · Laplace additive-noise bandit | cumulative regret | Helped |
| Apply adaptive bias-weighting instead of setting all weights to 1 (ablation) | LR confidence sets for UCB · Gaussian additive-noise bandit | cumulative regret | Helped |
| Use LR confidence sets instead of heuristic-confidence alternatives | UCB · Poisson bandit | cumulative regret | Helped |
| Use LR confidence sequences instead of sub-exponential confidence sets | UCB for transformed Weibull survival observations · Weibull survival analysis (p=2) | cumulative regret | Helped |
| Use LR confidence sets instead of heuristic confidence sets | UCB with RKHS payoff functions · Gaussian and Laplace additive-noise bandits | cumulative regret | No clear effect |
Closest papers by meaning
- A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits (NeurIPS 2024 · similarity 0.90)
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.89)
- Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means (NeurIPS 2026 · similarity 0.86)
- Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood (NeurIPS 2024 · similarity 0.86)
- Martingale Posterior Neural Networks for Fast Sequential Decision Making (NeurIPS 2025 · similarity 0.86)
- Kernel-based guarantees for nonlinear parametric models in Bayesian optimization (NeurIPS 2026 · similarity 0.85)
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.