Research map / Learning theory and algorithms / Optimal transport
Multivariate Soft Rank via Entropy-Regularized Optimal Transport: Sample Efficiency and Generative Modeling
Shoaib Bin Masud, Matthew Werenski, James M. Murphy, Shuchin Aeron
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 MMD loss with soft-rank energy (sRE) for generator training | MNIST latent generator · MNIST generation (latent dim 8) | GAN-train accuracy: 74.5 -> 86.6 | Improved |
| replace MMD loss with sRMMD for generator training | MNIST latent generator · MNIST generation (latent dim 8) | GAN-train accuracy: 74.5 -> 84.2 | Improved |
| replace MMD loss with sRE for generator training | MNIST latent generator · MNIST generation (latent dim 8) | GAN-test accuracy: 88.7 -> 95.6 | Improved |
| replace MMD loss with sRMMD for generator training | MNIST latent generator · MNIST generation (latent dim 8) | GAN-test accuracy: 88.7 -> 94.5 | Improved |
| use sRMMD knockoffs instead of MMD knockoffs | knockoff generator · IBD metabolomics knockoffs (q=0.05) | detection power (%): 63 -> 76 | Improved |
| use sRMMD knockoffs instead of second-order knockoffs | knockoff generator · IBD metabolomics knockoffs (q=0.05) | detection power (%): 69 -> 76 | Improved |
Closest papers by meaning
- Low-rank Optimal Transport: Approximation, Statistics and Debiasing (NeurIPS 2022 · similarity 0.88)
- Rank-guided Diffusion for Noise Few-Shot Learning (ICML 2026 · similarity 0.86)
- Unbalanced Low-rank Optimal Transport Solvers (NeurIPS 2023 · similarity 0.85)
- Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling (NeurIPS 2024 · similarity 0.85)
- Learning normalized image densities via dual score matching (NeurIPS 2025 · similarity 0.84)
- Multimarginal Generative Modeling with Stochastic Interpolants (ICLR 2024 · 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.
