Research map / Bandits and online learning / Online convex optimization and games
Coin Betting and Parameter-Free Online Learning
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 KT coin betting potentials to construct parameter-free OLO | OLO over Hilbert space · OLO over Hilbert space | per-round time complexity: This paper: \mathcal{O}(1) | Helped |
| Use the δ-shifted KT potential instead of the unshifted potential (ablation) | KT coin betting for LEA · LEA | regret bound: O(\sqrt{T (\log T + \KL{u}{\pi}}) -> O(\sqrt{T (1 + \KL{u}{\pi}}) | Helped |
| Use parameter-free algorithms rather than learning-rate-tuned Hedge | LEA on the synthetic Hadamard setting · Synthetic LEA, T=32768 | regret to the best expert | Mixed |
| Use the KT-based parameter-free algorithm | OCO solved through OLO · Three regression datasets | absolute loss | Helped |
Closest papers by meaning
- Online Learning in Betting Markets: Profit versus Prediction (ICML 2024 · similarity 0.87)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · similarity 0.87)
- High-Dimensional Prediction for Sequential Decision Making (ICML 2025 · similarity 0.86)
- Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality (NeurIPS 2025 · similarity 0.86)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.86)
- Online Learning under Budget and ROI Constraints via Weak Adaptivity (ICML 2024 · 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.