Summary of A Proximal Algorithm For Sampling, by Jiaming Liang et al.
A Proximal Algorithm for Sampling
by Jiaming Liang, Yongxin Chen
First submitted to arxiv on: 28 Feb 2022
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 This paper tackles challenging sampling problems involving non-smooth potentials, which can be either convex or non-convex. The authors propose a novel proximal sampling algorithm, inspired by optimization techniques, to efficiently sample from these complex distributions. By leveraging the alternating sampling framework (ASF) and rejection sampling, the proposed method achieves better complexity than existing methods in most cases. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a tricky problem in statistics that involves collecting data from special kinds of functions. These functions can be curved or straight-lined, and they’re not always easy to work with. The authors develop a new way to collect this data using an old method called Gibbs sampling, but with some clever tricks to make it faster and more accurate. This new approach is helpful because it can handle many different types of functions, and it’s better than what people have been doing before. |
Keywords
* Artificial intelligence * Optimization
