activity
20162025
most citedTheory of Deep Learning III: explaining the non-overfitting puzzle

49 citations · 170 across the 9 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

cs.LG2018★ 37 cited

Biologically-plausible learning algorithms can scale to large datasets

Will Xiao, Honglin Chen, Qianli Liao +1

The backpropagation (BP) algorithm is often thought to be biologically implausible in the brain. One of the main reasons is that BP requires symmetric weight matrices in the feedfo…

cs.LG2018

A Surprising Linear Relationship Predicts Test Performance in Deep Networks

Qianli Liao, Brando Miranda, Andrzej Banburski +2

Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalizat…

cs.LG2018

Theory IIIb: Generalization in Deep Networks

Tomaso Poggio, Qianli Liao, Brando Miranda +3

A main puzzle of deep neural networks (DNNs) revolves around the apparent absence of "overfitting", defined in this paper as follows: the expected error does not get worse when inc…

cs.LG2018★ 49 cited

Theory of Deep Learning III: explaining the non-overfitting puzzle

Tomaso Poggio, Kenji Kawaguchi, Qianli Liao +5

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on ra…

cs.LG2018★ 44 cited

Theory of Deep Learning IIb: Optimization Properties of SGD

Chiyuan Zhang, Qianli Liao, Alexander Rakhlin +3

In Theory IIb we characterize with a mix of theory and experiments the optimization of deep convolutional networks by Stochastic Gradient Descent. The main new result in this paper…