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: | , |
|---|---|
| 格式: | Internet publication |
| 语言: | English |
| 出版: |
2023
|