gradient-descent-finds-local-not-global-minima

IN premise — entries/2026/06/21/wiki-Backpropagation-chunk-5.md

Created 2026-06-21T09:55:49+00:00

Gradient descent with backpropagation finds local minima only, with no guarantee of reaching a global minimum; however, LeCun et al. argued this is often acceptable in practice for neural networks.

Dependents

These beliefs depend on this one:

• OUT gradient-descent-effective-global-optimizer — Gradient descent with backpropagation effectively finds global optima for neural network training in practice, despite lacking global guarantees.