Research map / Learning theory and algorithms / Prediction and decision losses
Online Search with Best-Price and Query-Based Predictions
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 an n-query robust binary search rather than RLIS's n candidate intervals (ablation) | Online search with query-based predictions · Currency exchange benchmarks | average profit | Helped |
| Use RBIS with H in {3, 5} (ablation) | RBIS · Currency exchange benchmarks | average profit | Helped |
| Increase the query error bound H (ablation) | RLIS and RBIS · Currency exchange benchmarks | average profit | Hurt |
| Use best-price predictions with small error instead of no prediction | ORA · Bitcoin-to-USD | average profit: η <0.5 | Helped |
| Use best-price predictions with small error instead of no prediction | ORA · Ethereum-to-USD | average profit: η < 0.2 | Helped |
| Use best-price predictions with small error instead of no prediction | ORA · Euro-to-USD and Yen-to-CAD | average profit: η <0.02 | Helped |
| Increase negative prediction error | Robust-Mix · Currency exchange benchmarks | average profit | Helped |
| Increase positive prediction error | Robust-Mix · Currency exchange benchmarks | average profit | Hurt |
| Use query-based predictions with reasonable error instead of no prediction | RLIS and RBIS · Currency exchange benchmarks | average profit | Helped |
| Increase the number of wrong query responses | RLIS and RBIS · Currency exchange benchmarks | average profit | Hurt |
| Use RBIS with H=8 instead of ONstar | RBIS · Currency exchange benchmarks | average profit: H=8 | Helped |
Closest papers by meaning
- Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search (ICML 2025 · similarity 0.91)
- A Parametric Contextual Online Learning Theory of Brokerage (ICML 2025 · similarity 0.86)
- Online Learning in Betting Markets: Profit versus Prediction (ICML 2024 · similarity 0.86)
- Learning to price with resource constraints: from full information to machine-learned prices (NeurIPS 2025 · similarity 0.86)
- Adaptive Market Making with Inventory Constraints via Online Learning (AAAI 2025 · similarity 0.86)
- Contextual Online Pricing with (Biased) Offline Data (NeurIPS 2025 · similarity 0.85)
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.