activity
20162019
most citedTheory of Deep Learning III: explaining the non-overfitting puzzle

49 citations · 52 across the 2 of their papers we have counts for

collaborators

8 papers

stat.ML20193 cited

Eliminating all bad Local Minima from Loss Landscapes without even adding an Extra Unit

Jascha Sohl-Dickstein, Kenji Kawaguchi

Recent work has noted that all bad local minima can be removed from neural network loss landscapes, by adding a single unit with a particular parameterization. We show that the cor…

cs.LG2019

Elimination of All Bad Local Minima in Deep Learning

Kenji Kawaguchi, Leslie Pack Kaelbling

In this paper, we theoretically prove that adding one special neuron per output unit eliminates all suboptimal local minima of any deep neural network, for multi-class classificati…

cs.LG2018

Effect of Depth and Width on Local Minima in Deep Learning

Kenji Kawaguchi, Jiaoyang Huang, Leslie Pack Kaelbling

In this paper, we analyze the effects of depth and width on the quality of local minima, without strong over-parameterization and simplification assumptions in the literature. With…

stat.ML2018

Depth with Nonlinearity Creates No Bad Local Minima in ResNets

Kenji Kawaguchi, Yoshua Bengio

In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense t…

stat.ML2018

Generalization in Machine Learning via Analytical Learning Theory

Kenji Kawaguchi, Yoshua Bengio, Vikas Verma +1

This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep…

cs.LG201849 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…