TL;DR
Natural Evolution Strategies (NES) are a family of black-box optimization algorithms that use natural gradients to efficiently update solution distributions, improving convergence and robustness over traditional evolutionary methods.
Contribution
This paper introduces NES algorithms with techniques to enhance convergence, robustness, and efficiency, and explores various distribution implementations for different optimization scenarios.
Findings
Achieved state-of-the-art results on standard benchmarks
Demonstrated robustness and efficiency in high-dimensional spaces
Compared favorably with existing evolutionary algorithms
Abstract
This paper presents Natural Evolution Strategies (NES), a recent family of algorithms that constitute a more principled approach to black-box optimization than established evolutionary algorithms. NES maintains a parameterized distribution on the set of solution candidates, and the natural gradient is used to update the distribution's parameters in the direction of higher expected fitness. We introduce a collection of techniques that address issues of convergence, robustness, sample complexity, computational complexity and sensitivity to hyperparameters. This paper explores a number of implementations of the NES family, ranging from general-purpose multi-variate normal distributions to heavy-tailed and separable distributions tailored towards global optimization and search in high dimensional spaces, respectively. Experimental results show best published performance on various standard…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
