Summary of Inverse Entropic Optimal Transport Solves Semi-supervised Learning Via Data Likelihood Maximization, by Mikhail Persiianov et al.
Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization
by Mikhail Persiianov, Arip Asadulaev, Nikita Andreev, Nikita Starodubcev, Dmitry Baranchuk, Anastasis Kratsios, Evgeny Burnaev, Alexander Korotin
First submitted to arxiv on: 3 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 learning paradigm integrates paired and unpaired data seamlessly through data likelihood maximization techniques. It connects with inverse entropic optimal transport (OT), allowing for the application of recent advances in computational OT to establish a light learning algorithm that learns conditional distributions using both types of data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to learn from data is being developed, which combines two kinds of information: paired data and unpaired data. Paired data comes with answers, while unpaired data doesn’t. Normally, we use one or the other, but this new approach uses both together. It works by maximizing a special kind of likelihood function. This method also connects to a concept called inverse entropic optimal transport (OT), which helps make the learning process faster and more efficient. |
Keywords
* Artificial intelligence * Likelihood
