Research map / Bandits and online learning / Online convex optimization and games
Online Linear Optimization with Many Hints
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 a learned convex combination of the hint sequences rather than choosing a single hint sequence | Constrained OLO with K hints · Constrained OLO with K hint sequences | regret bound | Helped |
| Choose among individual hint sequences with multiplicative weights instead of optimizing over their convex combinations | Constrained OLO with K hints · Constrained OLO with K hint sequences | regret bound | Hurt |
| Use a smoothed hinge loss over the hint simplex to select convex combinations | K-Hints_α · Constrained OLO with K hint sequences | regret bound | Helped |
| Combine candidate-threshold learners with the randomized combiner | Constrained OLO with unknown α · Constrained OLO with K hint sequences; unknown α | expected regret bound | Helped |
| Use a randomized rather than deterministic combiner for base learners | Constrained OLO combiner · Constrained OLO with K base algorithms; oblivious adversary | regret overhead: K to log_2(K+1) | Helped |
| Add multiple hint-specific one-dimensional learners to the unconstrained learner | Unconstrained OLO · Unconstrained OLO with K hint sequences | regret bound | Helped |
Closest papers by meaning
- Logarithmic Regret from Sublinear Hints (NeurIPS 2021 · similarity 0.94)
- Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound (NeurIPS 2025 · similarity 0.92)
- Fully Unconstrained Online Learning (NeurIPS 2024 · similarity 0.89)
- Dynamic Regret Reduces to Kernelized Static Regret (NeurIPS 2025 · similarity 0.89)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.88)
- Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods (ICML 2024 · similarity 0.88)
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.