Summary of Stereographic Spherical Sliced Wasserstein Distances, by Huy Tran et al.
Stereographic Spherical Sliced Wasserstein Distances
by Huy Tran, Yikun Bai, Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu, Rocio Diaz Martin, Soheil Kolouri
First submitted to arxiv on: 4 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
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 proposed Stereographic Spherical Sliced Wasserstein (S3W) distance efficiently compares spherical probability measures, leveraging the stereographic projection and generalized Radon transform. By addressing distortion issues and providing theoretical analysis, this metric offers a rotationally invariant variation, outperforming recent baselines in terms of speed and accuracy through various numerical studies, including gradient flows and self-supervised learning. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand spherical probability distributions better. It creates a fast way to compare these distributions using the stereographic projection and Radon transform. The team fixed some issues with this method and tested it on many problems. Their results show that their approach is faster and more accurate than other methods. |
Keywords
* Artificial intelligence * Probability * Self supervised