Correspondence between neuroevolution and gradient descent
arXiv:2008.06643 · doi:10.1038/s41467-021-26568-2
Abstract
We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise. Averaged over independent realizations of the learning process, neuroevolution is equivalent to gradient descent on the loss function. We use numerical simulation to show that this correspondence can be observed for finite mutations,for shallow and deep neural networks. Our results provide a connection between two families of neural-network training methods that are usually considered to be fundamentally different.
References in corpus (6)
- Deep Learning in Neural Networks: An Overview
- On the difficulty of training Recurrent Neural Networks
- Reversible self-assembly of patchy particles into monodisperse icosahedral clusters
- Revisiting the slow dynamics of a silica melt using Monte Carlo simulations
- On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent
- Evolution Strategies Converges to Finite Differences