News for hackers. Stuff that matters.

A comment on Diffusion Models Are Evolutionary Algorithms. Parent comment

Re:Diffusion Models Are Evolutionary Algorithms by Matumio on Monday November 18, 2024 @07:06AM (#42171688)
Can confirm. I've played around with differential evolution and a few others. Nothing was able to beat CMA-ES. At best, after some manual tuning it was just barely matching the untuned CMA-ES. (The task was to optimize a small neural network, gradients not easily available.)

CMA-ES is not suited for very large problems (more than a few hundred parameters), but there are several variants that can handle this, like sep-CMA-ES.

[ Parent | on HN ]
Re:Diffusion Models Are Evolutionary Algorithms by sevensor on Monday November 18, 2024 @08:23AM (#42172089)
Differential evolution definitely comes in second as far as I’ve seen. In fact, what I’ve seen is that evolutionary search operators are effective inversely proportional to how faithfully they model actual biological processes.
[ Parent | on HN ]