Research map / Learning theory and algorithms / Optimal transport
Geometric Losses for Distributional Learning
Arthur Mensch, Mathieu Blondel, Gabriel Peyré
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 |
|---|---|---|---|
| Replace multinomial logistic loss with g-logistic loss using ordinal cost | Linear ordinal regression · Ordinal regression datasets (30-fold cross-validation) | Haus. div.: .46±.12 -> .44±.08 | Improved |
| Replace multinomial logistic loss with g-logistic loss using ordinal cost | Linear ordinal regression · Ordinal regression datasets (30-fold cross-validation) | MAE: .44±.09 -> .45±.09 | Hurt |
| Replace multinomial logistic loss with g-logistic loss using ordinal cost | Linear ordinal regression · Ordinal regression datasets (30-fold cross-validation) | Acc.: .66±.07 -> .65±.07 | Hurt |
| Replace standard softmax and KL loss with g-softmax and geometric loss | VAE drawing reconstruction · QuickDraw Cat and MNIST | Asymmetric Hausdorff divergence | Improved |
Closest papers by meaning
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification (NeurIPS 2025 · similarity 0.86)
- Supervised Distributional Reduction via Optimal Transport and Dependence Maximization (NeurIPS 2026 · similarity 0.86)
- Learning with Fitzpatrick Losses (NeurIPS 2024 · similarity 0.86)
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (ICML 2024 · similarity 0.85)
- An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph (NeurIPS 2025 · similarity 0.85)
- Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation (NeurIPS 2026 · 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.
