Summary of Submodular Framework For Structured-sparse Optimal Transport, by Piyushi Manupriya and Pratik Jawanpuria and Karthik S. Gurumoorthy and Sakethanath Jagarlapudi and Bamdev Mishra
Submodular Framework for Structured-Sparse Optimal Transport
by Piyushi Manupriya, Pratik Jawanpuria, Karthik S. Gurumoorthy, SakethaNath Jagarlapudi, Bamdev Mishra
First submitted to arxiv on: 7 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper explores learning sparse transport plans within the unbalanced optimal transport (UOT) framework, which has gained attention for its flexible handling of un-normalized measures and robustness properties. The authors propose novel sparsity-constrained UOT formulations, building on maximum mean discrepancy based UOT, and develop efficient gradient-based discrete greedy algorithms with theoretical guarantees. The approach selects a diverse support set and is illustrated in various applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at ways to make transportation plans more efficient by making some parts of the plan “sparse”, meaning they don’t use all the available space. This can be useful when trying to move data or objects from one place to another. The authors come up with new ways to solve this problem and test their ideas on different tasks to see how well they work. |
Keywords
» Artificial intelligence » Attention
