Research map / Bandits and online learning / Online convex optimization and games
PDE-Based Optimal Strategy for Unconstrained 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 the V̄₁/₂ potential instead of V̄₋₁/₂ (ablation) | PDE-based unconstrained OLO · Synthetic OCO, u*=10 | cumulative loss (regret) | Helped |
| Use the V̄₁/₂ potential instead of V̄₋₁/₂ (ablation) | PDE-based unconstrained OLO · Synthetic OCO, far-away comparators | cumulative loss (regret) | Helped |
| Use the V̄₁/₂ potential instead of V̄₋₁/₂ (ablation) | PDE-based unconstrained OLO · Synthetic OCO, small |u*| | cumulative loss (regret) | Hurt |
| Use a V̄₁/₂ potential with a more permissive loss-regret trade-off | PDE-based unconstrained OLO · Unconstrained OLO | regret for large comparators | Helped |
Closest papers by meaning
- Fully Unconstrained Online Learning (NeurIPS 2024 · similarity 0.87)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · similarity 0.87)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.87)
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.86)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.86)
- Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound (NeurIPS 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.