Back to Results
First PageMeta Content



We show that any model trained by a stochastic gradient method with few iterations has vanishing generalization error. We prove this by showing the method is algorithmically stable in the sense of Bousquet and Elisseeff.
Add to Reading List

Document Date: 2016-06-23 15:50:48


Open Document

File Size: 10,63 KB

Share Result on Facebook
UPDATE