Summary of Double Variance Reduction: a Smoothing Trick For Composite Optimization Problems Without First-order Gradient, by Hao Di et al.
Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
by Hao Di, Haishan Ye, Yueling Zhang, Xiangyu Chang, Guang Dai, Ivor W. Tsang
First submitted to arxiv on: 28 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Optimization and Control (math.OC)
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 Zeroth-order Proximal Double Variance Reduction (ZPDVR) method reduces both sampling and coordinate-wise variances in composite optimization problems, relying solely on random gradient estimates. This approach achieves optimal query complexity in the strongly convex and smooth setting, outperforming other related methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way to make computers find the best solution more efficiently by reducing noise in calculations. It uses an averaging trick to get better results without having to calculate too many partial derivatives. This makes it faster and more accurate for big problems with lots of variables. |
Keywords
* Artificial intelligence * Optimization
