Generalization bounds for label noise stochastic gradient descent
We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions. Under a suitable choice of semimetric, we establish a contraction in Wasserstein distance of the label noise stochastic gradient...
| Main Authors: | , |
|---|---|
| Formato: | Internet publication |
| Idioma: | English |
| Publicado em: |
2023
|