[1Z2] [General Session] 2. Machine Learning

[1Z2-01] Robustness verification of CMA-ES optimization for neural networks

〇Hiroki Shimizu¹, Junpei Komiyama², Masashi Toyoda² (1. The University of Tokyo, 2. Institute of Industrial Science, the University of Tokyo)

Keywords:Evolutionary algorithm, Optimization, Machine learning

This paper aims to verify robustness of covariance matrix adaptation evolution strategy (CMA-ES) optimization for neural networks (NN). We added label noise to the training dataset. Unlike stochastic gradient descent (SGD), which is the state-of-the-art optimizer of NN, a CMA-ES based optimization was robust against label noise.