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.

First Page		Document Content
Date: 2016-06-23 15:50:48		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 Source URL: mmds-data.org Download Document from Source Website File Size: 10,63 KB Share Document on Facebook