Research map / Bandits and online learning / Online convex optimization and games
Spectral bandits
Tomáš Kocák, Rémi Munos, Branislav Kveton, Shipra Agrawal, Michal Valko
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 |
|---|---|---|---|
| make the reward function smoother (fewer nonzero eigenvector components: 500 -> 5) (ablation) | SpectralTS · BA graph 500 nodes, T=100 | cumulative regret: 123.79 -> 7.99 | Improved |
| make the reward function smoother (500 -> 5 nonzero components) (ablation) | SpectralUCB · BA graph 500 nodes, T=100 | cumulative regret: 130.54 -> 3.05 | Improved |
| use graph-spectral algorithms instead of LinearTS/LinUCB | SpectralTS and SpectralUCB · Erdos-Renyi, lattice, Barabasi-Albert graphs (N=500, T=100) | cumulative regret | Improved |
| use lazy updates for UCB computation (ablation) | SpectralUCB · running time vs number of actions | computational time | Improved |
| use only first L=200 (10%) eigenvectors instead of all 2000 (ablation) | SpectralUCB · MovieLens single user, N=2019 | cumulative regret and running time | No clear effect |
| use spectral algorithms instead of linear ones | SpectralTS and SpectralUCB · MovieLens (400 users, 618 movies), T=500 | cumulative regret | Improved |
Closest papers by meaning
- Laplacian Kernelized Bandit (ICLR 2026 · similarity 0.89)
- Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces (ICML 2022 · similarity 0.87)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · similarity 0.87)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.87)
- From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards (NeurIPS 2025 · similarity 0.86)
- Leveraging Offline Data in Linear Latent Contextual Bandits (ICML 2025 · 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.
