Summary of Gradient Compressed Sensing: a Query-efficient Gradient Estimator For High-dimensional Zeroth-order Optimization, by Ruizhong Qiu et al.
Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization
by Ruizhong Qiu, Hanghang Tong
First submitted to arxiv on: 27 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 proposes a new method for nonconvex zeroth-order optimization (ZOO) in high-dimensional spaces, specifically designed to leverage gradient sparsity. The authors aim to reduce the dependence on dimensionality by designing efficient gradient estimators. Their proposed algorithm, Gradient Compressed Sensing (GraCe), uses only O(s log log d/s) queries per step and achieves O(1/T) convergence rate. This improves upon previous methods that required O(s log d/s) queries per step for the same convergence rate. The authors demonstrate the effectiveness of GraCe by generalizing the Indyk-Price-Woodruff (IPW) algorithm from linear measurements to nonlinear functions, and improving it via a dependent random partition technique. Experimental results show that GraCe outperforms existing ZOO methods on 10000-dimensional function benchmarks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper is about finding the best way to optimize functions in very high-dimensional spaces. The authors are trying to solve this problem by taking advantage of the fact that the gradients (which are like partial derivatives) of these functions are often sparse, meaning they have many zero values. They propose a new algorithm called Gradient Compressed Sensing (GraCe) that is more efficient than previous methods and can handle high-dimensional spaces. The authors test GraCe on large function benchmarks and show that it performs better than other existing algorithms. |
Keywords
» Artificial intelligence » Optimization
