How consensus-based optimization can be interpreted as a stochastic relaxation of gradient descent
We provide a novel analytical perspective on the theoretical understanding of gradient-based learning algorithms by interpreting consensus-based optimization (CBO), a recently proposed multi-particle derivative-free optimization method, as a stochastic relaxation of gradient descent. Remarkably, we...
| Hauptverfasser: | , , , |
|---|---|
| Format: | Conference item |
| Sprache: | English |
| Veröffentlicht: |
OpenReview
2024
|