Research map / Learning theory and algorithms / Optimal transport
Differentiable Ranking and Sorting using Optimal Transport
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 Sinkhorn sorting instead of Stochastic NeuralSort | Neural sort task · n=3, 5, 7, 9, 15 | sorting precision (exact; partial): 0.920 (0.946) -> 0.928 (0.950); 0.790 (0.907) -> 0.811 (0.917); 0.636 (0.873) -> 0.656 (0.882); 0.452 (0.829) -> 0.497 ( | Helped |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · bio, τ=50% and τ=90% | training quantile error: 0.33 -> 0.28; 1.17 -> 1.15 | Helped |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · bike, τ=50% and τ=90% | training quantile error: 0.23 -> 0.14; 0.76 -> 0.69 | Helped |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · facebook, τ=50% and τ=90% | training quantile error: 0.00 -> 0.04; 0.21 -> 0.27 | Mixed |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · star, τ=50% and τ=90% | training quantile error: 0.55 -> 0.33; 1.29 -> 1.15 | Helped |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · concrete, τ=50% and τ=90% | training quantile error: 0.35 -> 0.25; 0.83 -> 0.72 | Helped |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · community, τ=50% and τ=90% | training quantile error: 0.27 -> 0.06; 0.77 -> 0.56 | Helped |
| Replace empirical quantile selection with the soft quantile operator | Least quantile regression · Least quantile regression datasets, test quantile error and MSE | test quantile error and MSE | Mixed |
Closest papers by meaning
- Fast Differentiable Sorting and Ranking (ICML 2020 · similarity 0.92)
- Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision (ICML 2021 · similarity 0.89)
- Monotonic Differentiable Sorting Networks (ICLR 2022 · similarity 0.89)
- Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions (ICLR 2024 · similarity 0.85)
- LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection (ICML 2025 · similarity 0.84)
- Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms (NeurIPS 2024 · similarity 0.81)
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.