Skip to main content

Provable bounds for learning some deep representations

Author(s): Arora, Sanjeev; Bhaskara, A; Ge, R; Ma, T

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr18x5s
Full metadata record
DC FieldValueLanguage
dc.contributor.authorArora, Sanjeev-
dc.contributor.authorBhaskara, A-
dc.contributor.authorGe, R-
dc.contributor.authorMa, T-
dc.date.accessioned2019-08-29T17:05:02Z-
dc.date.available2019-08-29T17:05:02Z-
dc.date.issued2014en_US
dc.identifier.citationArora, S, Bhaskara, A, Ge, R, Ma, T. (2014). Provable bounds for learning some deep representations. 1 (883 - 891en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr18x5s-
dc.description.abstract2014 We give algorithms with provable guarantees that learn a class of deep nets in the generative model view popularized by Hinton and others. Our generative model is an n node multilayer network that has degree at most nγ for some γ < 1 and each edge has a random edge weight in [-1,1]. Our algorithm learns almost all networks in this class with polynomial running time. The sample complexity is quadratic or cubic depending upon the details of the model. The algorithm uses layerwise learning. It is based upon a novel idea of observing correlations among features and using these to infer the underlying edge structure via a global graph recovery procedure. The analysis of the algorithm reveals interesting structure of neural nets with random edge weights.en_US
dc.format.extent883 - 891en_US
dc.language.isoen_USen_US
dc.relation.ispartof31st International Conference on Machine Learningen_US
dc.rightsAuthor's manuscripten_US
dc.titleProvable bounds for learning some deep representationsen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
Provable Bounds for Learning Some Deep Representations.pdf566.36 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.