Summary of Eigenvi: Score-based Variational Inference with Orthogonal Function Expansions, by Diana Cai et al.
EigenVI: score-based variational inference with orthogonal function expansions
by Diana Cai, Chirag Modi, Charles C. Margossian, Robert M. Gower, David M. Blei, Lawrence K. Saul
First submitted to arxiv on: 31 Oct 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Computation (stat.CO)
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 introduces EigenVI, an eigenvalue-based approach for black-box variational inference (BBVI). The method constructs variational approximations using orthogonal function expansions, which provide a flexible and simple way to model complex distributions. By minimizing the Fisher divergence, EigenVI effectively sidesteps iterative gradient-based optimizations, making it more accurate and robust than existing methods for Gaussian BBVI. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary EigenVI is a new way to do something called black-box variational inference. It uses special functions to make predictions about what things might look like if they’re not exactly the same as we’ve seen before. This helps us understand things that are hard to know just by looking at them. EigenVI works well on lots of different types of problems, and it’s better than some other methods at guessing what things might be. |
Keywords
* Artificial intelligence * Inference
