Summary of A Survey on Domain Adaptation Theory: Learning Bounds and Theoretical Guarantees, by Ievgen Redko et al.
A survey on domain adaptation theory: learning bounds and theoretical guarantees
by Ievgen Redko, Emilie Morvant, Amaury Habrard, Marc Sebban, Younès Bennani
First submitted to arxiv on: 24 Apr 2020
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 paper presents an overview of the state-of-the-art theoretical results in domain adaptation, a sub-field of transfer learning that enables machines to learn from one task and apply it to another with similar characteristics. Domain adaptation assumes a changing data distribution between training and test datasets, while the learning task remains constant. The authors provide a comprehensive description of existing results on learning bounds based on different statistical learning frameworks, highlighting key concepts such as transfer learning, semi-supervised learning, and supervised learning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Domain adaptation is a way for machines to learn from one task and use that knowledge in another task with similar characteristics. This can help reduce the need for new labeled data. The paper looks at what we know so far about this process, using different types of statistical frameworks. It’s like how humans can learn something once and then apply it to a similar situation later on. |
Keywords
* Artificial intelligence * Domain adaptation * Semi supervised * Supervised * Transfer learning
