Research map / Learning theory and algorithms / Prediction and decision losses

Toward Minimal-dimensional Convex Calibrated Surrogate Losses for Classification with Rejection

NeurIPS 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Consistency of surrogate losses

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies convex calibrated surrogate losses for classification with rejection, aiming to minimize the dimensionality of the scoring functions used.

Problem

Designing convex calibrated surrogate losses for classification with rejection (CwR), where rejection has cost c smaller than misclassification cost, with the goal of reducing the dimensionality of the scoring functions below K for K-class classification.

Approach

Builds on prior evidence that the dimensionality of surrogate scoring functions for K-class classification can be reduced, and seeks minimal-dimensional convex calibrated surrogates for CwR. Only the abstract is available, so the specific construction is not stated.

Closest papers by meaning

• Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification (NeurIPS 2024 · similarity 0.89)
• A Universal Growth Rate for Learning with Smooth Surrogate Losses (NeurIPS 2024 · similarity 0.87)
• Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification (NeurIPS 2025 · similarity 0.86)
• Improved Balanced Classification with Theoretically Grounded Loss Functions (NeurIPS 2025 · similarity 0.86)
• Consistency Conditions for Differentiable Surrogate Losses (NeurIPS 2025 · similarity 0.85)
• EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification (ICML 2025 · similarity 0.85)