Research map / Learning theory and algorithms / Prediction and decision losses
Best Response Regression
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 |
|---|---|---|---|
| Best-response agent versus LSE opponent trained on train set only | MILP agent · Boston Housing | test payoff: 0.641 | Helped |
| Opponent also sees test set (ALL instead of TRAIN) against LSE (ablation) | MILP agent · Boston Housing | test payoff: 0.641 -> 0.645 | No clear effect |
| Opponent also sees test set (ALL instead of TRAIN) against LAE (ablation) | MILP agent · Boston Housing | test payoff: 0.570 -> 0.528 | Hurt |
| Opponent also sees test set (ALL instead of TRAIN) against LSE (ablation) | MILP agent · Boston Housing | train payoff: 0.699 -> 0.711 | Helped |
| Opponent also sees test set (ALL instead of TRAIN) against LAE (ablation) | MILP agent · Boston Housing | train payoff: 0.621 -> 0.625 | Helped |
| Opponent uses LAE instead of LSE | MILP agent · Boston Housing, TRAIN | train payoff: 0.699 -> 0.621 | Hurt |
| Opponent uses LAE instead of LSE | MILP agent · Boston Housing, ALL | test payoff: 0.645 -> 0.528 | Hurt |
| Agent plays best response instead of minimizing classical loss | MILP agent · Boston Housing, LSE opponent | classical loss ratio (training set): 1.007 | Hurt |
| Agent plays best response instead of minimizing classical loss | MILP agent · Boston Housing, LSE opponent | MSE ratio (test set): 0.999 | Helped |
| Agent plays best response versus LAE opponent | MILP agent · Boston Housing, LAE opponent | classical loss ratio (test set): 1.002 | No clear effect |
Closest papers by meaning
- Horizon-Independent Minimax Linear Regression (NeurIPS 2018 · similarity 0.87)
- Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach (ICML 2024 · similarity 0.86)
- Adversarial Regression with Multiple Learners (ICML 2018 · similarity 0.85)
- Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination (NeurIPS 2021 · similarity 0.85)
- A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) (AAAI 2024 · similarity 0.84)
- One-Shot Strategic Classification Under Unknown Costs (ICML 2024 · 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.