Guided evolutionary strategies: Augmenting random search with surrogate gradients

TL;DR

Guided Evolutionary Strategies enhance optimization by combining surrogate gradients with random search, improving performance in scenarios where true gradients are unavailable or intractable.

Contribution

The paper introduces a novel method that optimally integrates surrogate gradients with evolutionary strategies, including a new search distribution and hyperparameter tuning for better optimization.

Findings

Improved optimization performance over standard methods

Effective in problems with surrogate or intractable gradients

Provides a practical implementation with demonstrated results

Abstract

Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is available instead. This arises when an approximate gradient is easier to compute than the full gradient (e.g. in meta-learning or unrolled optimization), or when a true gradient is intractable and is replaced with a surrogate (e.g. in certain reinforcement learning applications, or when using synthetic gradients). We propose Guided Evolutionary Strategies, a method for optimally using surrogate gradient directions along with random search. We define a search distribution for evolutionary strategies that is elongated along a guiding subspace spanned by the surrogate gradients. This allows us to estimate a descent direction which can then be passed to a first-order optimizer. We analytically and numerically characterize the tradeoffs that result from tuning how strongly the search distribution is stretched along the guiding subspace, and we use this to derive a setting of the hyperparameters that works well across problems. Finally, we apply our method to example problems, demonstrating an improvement over both standard evolutionary strategies and first-order methods (that directly follow the surrogate gradient). We provide a demo of Guided ES at https://github.com/brain-research/guided-evolutionary-strategies