Toggle navigation
PDFSEARCH.IO
Document Search Engine - browse more than 18 million documents
Sign up
Sign in
Back to Results
First Page
Meta Content
View Document Preview and Link
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
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.