Research map / Bandits and online learning / Online convex optimization and games
Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems
Bo Sun, Russell Lee, Mohammad Hajiesmaili, Adam Wierman, Danny Tsang
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 learning-augmented OTA with online-learned robustness parameter instead of the worst-case optimal algorithm | OTA for BTC to USD conversion · BTC-USD one-week conversion, error level 1.0 | upper boxplot whisker of profit ratio: 1.35 -> 1.25 | Improved |
| raise crash probability to 0.45 for the worst-case optimized algorithm | worst-case optimized online algorithm · BTC-USD, error level 1.0 | profit ratio | Hurt |
| raise crash probability for the learning-augmented OTA (online-learned and offline-best lambda) | learning-augmented OTA · BTC-USD, error level 1.0 | profit ratio | No clear effect |
| online-learned lambda instead of offline-best lambda | learning-augmented OTA · BTC-USD one-week conversion | upper boxplot whisker of profit ratio | No clear effect |
Closest papers by meaning
- Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search (ICML 2025 · similarity 0.86)
- Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms (NeurIPS 2024 · similarity 0.85)
- Learning-Augmented Online Bipartite Fractional Matching (NeurIPS 2025 · similarity 0.83)
- Learning-Augmented Online Bidding in Stochastic Settings (NeurIPS 2025 · similarity 0.83)
- Near-Optimal Consistency-Robustness Trade-Offs for Learning-Augmented Online Knapsack Problems (ICML 2025 · similarity 0.83)
- Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions (ICML 2025 · similarity 0.83)
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.
