Summary of Expected Sliced Transport Plans, by Xinran Liu et al.
Expected Sliced Transport Plans
by Xinran Liu, Rocío Díaz Martín, Yikun Bai, Ashkan Shahbazi, Matthew Thorpe, Akram Aldroubi, Soheil Kolouri
First submitted to arxiv on: 16 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Metric Geometry (math.MG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel framework called Expected Sliced Transport (EST) plans to address the limitations of sliced-Wasserstein approaches in solving optimal transport (OT) problems. The EST plan is constructed by lifting one-dimensional OT plans back to the original space, allowing for the definition of a metric between discrete probability measures. This approach builds upon recent work on min-SWGG and demonstrates improved performance through illustrative numerical examples. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper solves an important problem in machine learning called optimal transport (OT). It shows how to make OT more efficient by using slices of high-dimensional data. The new method, called Expected Sliced Transport (EST), can be used to define a metric between two probability measures. This is useful for comparing and matching different types of data. |
Keywords
» Artificial intelligence » Machine learning » Probability
