Research map / Learning theory and algorithms / Prediction and decision losses
Optimal Binary Classifier Aggregation for General Losses
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 a general loss (non-convex partial losses allowed) for the minimax aggregation game, with the slack function minimized over ensemble weights instead of an ad hoc predictor | semi-supervised binary ensemble aggregation (minimax optimal predictor) · theoretical analysis, general losses satisfying monotone partial-loss assumption | minimax worst-case expected loss | No clear effect |
| Add convexity condition (A), (B), or (C) on the partial losses (e.g., convex partial losses, proper loss, or l_-' l_+'' >= l_-'' l_+') | slack function / potential well Psi · theoretical analysis of convexity of the potential well | convexity of the slack function | Helped |
Closest papers by meaning
- The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning (NeurIPS 2018 · similarity 0.88)
- Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification (NeurIPS 2026 · similarity 0.85)
- EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification (ICML 2025 · similarity 0.85)
- Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing (NeurIPS 2025 · similarity 0.84)
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification (NeurIPS 2025 · similarity 0.84)
- Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation (ICML 2025 · similarity 0.84)
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.