Weight Adaptation for Improving Parallel Performance of Adaptive Stochastic Natural Gradient
The paper proposes Weight Adaptation ASNG, a probabilistic model-based evolutionary algorithm that adapts its weight parameters to improve optimization efficiency and robustness.
The paper introduces a novel weight adaptation mechanism that improves the efficiency and robustness of probabilistic model-based evolutionary algorithms.
Keywords
Before reading this…
Applications
- →optimization problems
- →black-box optimization
To understand this paper, make sure you know these concepts first:
- probabilistic model-based evolutionary algorithmsfind papers →
- adaptive stochastic natural gradientfind papers →
Abstract
More Like ThisProbabilistic model-based evolutionary algorithms are promising for black-box optimization. Specifically, the adaptive stochastic natural gradient (ASNG) adaptively updates its learning rate, a typical hyperparameter in probabilistic model-based evolutionary algorithms, thereby realizing efficient and robust optimization. Although weight parameters are common hyperparameters, with the increasing demand for parallel evaluation of time-consuming tasks, it remains unclear how to set suitable weights for larger population sizes. In this paper, we propose Weight Adaptation ASNG (WA-ASNG), which incorporates a weight adaptation mechanism into ASNG. We calculated the estimated signal of the update direction from the accumulations of the natural gradient. Then, to maximize the signal, WA-ASNG adaptively updates its weight parameters by a gradient ascent over the optimization. While the learning rate adaptation plays a role in satisfying a sufficient condition for monotonic improvement of the expected objective value, the mechanism of weight adaptation is intended to maximize this improvement. The experimental results demonstrate that WA-ASNG outperforms PBIL and ASNG across various settings with population sizes ranging from 25 to 100 for binary optimization problems. Furthermore, WA-ASNG can perform efficiently in the presence of strong noise. Our code is available at https://github.com/shiralab/WA-ASNG .