# Optimal Transport on LSE Log-Sum-Exp potential synthetic data

Source: [Optimal Transport on LSE Log-Sum-Exp potential synthetic data](<https://www.sota2.com/research/sota/optimal-transport-on-lse-log-sum-exp-potential-synthetic-data>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:42:08.755Z

Evaluation of Optimal Transport algorithms on the LSE Log-Sum-Exp potential synthetic dataset, measured using metrics such as εμ(fi0), εμ(fi1), and Rank.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Optimal Transport |
| Dataset (including any stated split) | LSE Log-Sum-Exp potential synthetic data |
| Metric | Epsilon Mu (fi0) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Epsilon Mu (fi0)](<https://www.sota2.com/research/sota/optimal-transport-on-lse-log-sum-exp-potential-synthetic-data.md?metric=Epsilon%20Mu%20(fi0)>): Lower is better; unit: SCALAR.

- [Epsilon Mu (fi1)](<https://www.sota2.com/research/sota/optimal-transport-on-lse-log-sum-exp-potential-synthetic-data.md?metric=Epsilon%20Mu%20(fi1)>): Lower is better; unit: SCALAR.

- [Rank](<https://www.sota2.com/research/sota/optimal-transport-on-lse-log-sum-exp-potential-synthetic-data.md?metric=Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Epsilon Mu (fi0) | Result date | Report paper |
| --- | --- | --- | --- |
| Selection via semi-dual Brenier objective | 0.006 | Not recorded | 68fa59fe1e209131ce9bc1d9 |

### Selection via semi-dual Brenier objective

Epsilon Mu (fi0): 0.006. Result ID: 698bab3f7a967eddb77075bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa59fe1e209131ce9bc1d9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa59fe1e209131ce9bc1d9.md>)

[Implementation](<https://github.com/AmirTag/OT-ICNN>)

Recorded evaluation configuration: {"Selection Criterion":"Semi-dual Brenier objective","Number of candidate models":"64"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.