Musings on Deep Learning: Properties of SGD
[previously titled "Theory of Deep Learning III: Generalization Properties of SGD"] In Theory III we characterize with a mix of theory and experiments the generalization properties of Stochastic Gradient Descent in overparametrized deep convolutional networks. We show that Stochastic Gradi...
Main Authors: | Zhang, Chiyuan, Liao, Qianli, Rakhlin, Alexander, Sridharan, Karthik, Miranda, Brando, Golowich, Noah, Poggio, Tomaso |
---|---|
Format: | Technical Report |
Language: | en_US |
Published: |
Center for Brains, Minds and Machines (CBMM)
2017
|
Online Access: | http://hdl.handle.net/1721.1/107841 |
Similar Items
-
Theory of Deep Learning IIb: Optimization Properties of SGD
by: Zhang, Chiyuan, et al.
Published: (2018) -
Classical generalization bounds are surprisingly tight for Deep Networks
by: Liao, Qianli, et al.
Published: (2018) -
SGD Noise and Implicit Low-Rank Bias in Deep Neural Networks
by: Galanti, Tomer, et al.
Published: (2022) -
Theory IIIb: Generalization in Deep Networks
by: Poggio, Tomaso, et al.
Published: (2018) -
Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?
by: Poggio, Tomaso, et al.
Published: (2016)