Critical percolation as a framework to analyze the training of deep networks

Zohar Ringel, Rodrigo De Bem

Research output: Contribution to conferencePaperpeer-review

Abstract

In this paper we approach two relevant deep learning topics: i) tackling of graph structured input data and ii) a better understanding and analysis of deep networks and related learning algorithms. With this in mind we focus on the topological classification of reachability in a particular subset of planar graphs (Mazes). Doing so, we are able to model the topology of data while staying in Euclidean space, thus allowing its processing with standard CNN architectures. We suggest a suitable architecture for this problem and show that it can express a perfect solution to the classification task. The shape of the cost function around this solution is also derived and, remarkably, does not depend on the size of the maze in the large maze limit. Responsible for this behavior are rare events in the dataset which strongly regulate the shape of the cost function near this global minimum. We further identify an obstacle to learning in the form of poorly performing local minima in which the network chooses to ignore some of the inputs. We further support our claims with training experiments and numerical analysis of the cost function on networks with up to 128 layers.

Original languageAmerican English
StatePublished - 2018
Event6th International Conference on Learning Representations, ICLR 2018 - Vancouver, Canada
Duration: 30 Apr 20183 May 2018

Conference

Conference6th International Conference on Learning Representations, ICLR 2018
Country/TerritoryCanada
CityVancouver
Period30/04/183/05/18

Bibliographical note

Publisher Copyright:
© Learning Representations, ICLR 2018 - Conference Track Proceedings.All right reserved.

Fingerprint

Dive into the research topics of 'Critical percolation as a framework to analyze the training of deep networks'. Together they form a unique fingerprint.

Cite this