Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters
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 CMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Raisin | Mean Acc: 0.764 ± 0.019 -> 0.818 ± 0.018 | Improved |
| Use CMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Maternal | Mean Acc: 0.722 ± 0.019 -> 0.744 ± 0.020 | Improved |
| Use CMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Banknotes | Mean Acc: 0.929 ± 0.006 -> 0.954 ± 0.005 | Improved |
| Use AMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Raisin | Mean Acc: 0.764 ± 0.019 -> 0.800 ± 0.017 | Improved |
| Use AMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Maternal | Mean Acc: 0.722 ± 0.019 -> 0.736 ± 0.020 | Improved |
| Use AMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Banknotes | Mean Acc: 0.929 ± 0.006 -> 0.948 ± 0.005 | Improved |
| Use CMM-UCB instead of AMM-UCB | Linear bandits tuning SVM hyperparameters · Raisin | Mean Acc: 0.800 ± 0.017 -> 0.818 ± 0.018 | Improved |
| Use CMM-UCB instead of AMM-UCB | Linear bandits tuning SVM hyperparameters · Maternal | Mean Acc: 0.736 ± 0.020 -> 0.744 ± 0.020 | Improved |
| Use CMM-UCB instead of AMM-UCB | Linear bandits tuning SVM hyperparameters · Banknotes | Mean Acc: 0.948 ± 0.005 -> 0.954 ± 0.005 | Improved |
| Use CMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Raisin | Max Acc: 0.891 ± 0.019 -> 0.893 ± 0.019 | No clear effect |
| Use CMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Maternal | Max Acc: 0.827 ± 0.022 -> 0.829 ± 0.023 | No clear effect |
| Use CMM-UCB instead of OFUL | Linear bandits tuning SVM hyperparameters · Banknotes | Max Acc: 1.000 ± 0.000 -> 1.000 ± 0.000 | No clear effect |
Closest papers by meaning
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.92)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.90)
- Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards (NeurIPS 2025 · similarity 0.89)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.89)
- Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits (ICLR 2025 · similarity 0.89)
- Constrained Linear Thompson Sampling (NeurIPS 2025 · similarity 0.89)
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.
