Research map / Learning theory and algorithms / Optimal transport
Monotonic Differentiable Sorting Networks
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 |
|---|---|---|---|
| Replace logistic sigmoid with monotonic sigmoid relaxations | Differentiable sorting networks · MNIST n=15 | full rankings correctly identified: 23.5 -> 31.8 | Helped |
| Replace logistic sigmoid with monotonic sigmoid relaxations | Differentiable sorting networks · SVHN n=15 | full rankings correctly identified: 2.4 -> 13.7 | Helped |
| Use optimal sigmoid rather than Cauchy CDF (ablation) | Differentiable sorting networks · MNIST odd-even n=15 | full rankings correctly identified: 31.1 -> 31.8 | Helped |
| Use Cauchy CDF rather than optimal sigmoid (ablation) | Differentiable sorting networks · MNIST bitonic n=16 | full rankings correctly identified: 28.4 -> 29.0 | Helped |
| Use Cauchy CDF rather than optimal sigmoid (ablation) | Differentiable sorting networks · MNIST bitonic n=32 | full rankings correctly identified: 1.4 -> 1.6 | Helped |
| Use optimal sigmoid rather than Cauchy CDF (ablation) | Differentiable sorting networks · MNIST odd-even n=32 | full rankings correctly identified: 0.8 -> 1.4 | Helped |
| Use Cauchy CDF rather than optimal sigmoid (ablation) | Differentiable sorting networks · SVHN bitonic n=16 | full rankings correctly identified: 10.6 -> 12.2 | Helped |
| Replace the logistic sigmoid with the reciprocal sigmoid (ablation) | Differentiable sorting networks · MNIST n=3 | full rankings correctly identified: 94.3 -> 94.4 | No clear effect |
| Tune inverse temperature for the monotonic sigmoid (ablation) | Monotonic differentiable sorting networks · MNIST sorting tasks | individual element ranks correctly identified | Helped |
Closest papers by meaning
- Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision (ICML 2021 · similarity 0.92)
- Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions (ICLR 2024 · similarity 0.90)
- LapSum - One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection (ICML 2025 · similarity 0.85)
- Differentiable Quadratic Optimization For the Maximum Independent Set Problem (ICML 2025 · similarity 0.82)
- Geometric Algorithms for Neural Combinatorial Optimization with Constraints (NeurIPS 2025 · similarity 0.82)
- Differentiable extensions with rounding guarantees for combinatorial optimization over permutations (NeurIPS 2025 · 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.