A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case

Greg Ongie; Rebecca Willett; Daniel Soudry; Nathan Srebro

A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case

Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro

Technion - Israel Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We give a tight characterization of the (vectorized Euclidean) norm of weights required to realize a function as a single hidden-layer ReLU network with an unbounded number of units (infinite width), extending the univariate characterization of Savarese et al. (2019) to the multivariate case.

Original language	English
Title of host publication	8th International Conference on Learning Representations, ICLR 2020
State	Published - 2020
Event	8th International Conference on Learning Representations, ICLR 2020 - Addis Ababa, Ethiopia Duration: 30 Apr 2020 → …

Conference

Conference	8th International Conference on Learning Representations, ICLR 2020
Country/Territory	Ethiopia
City	Addis Ababa
Period	30/04/20 → …

All Science Journal Classification (ASJC) codes

Education
Language and Linguistics
Computer Science Applications
Linguistics and Language

Access to Document

https://openreview.net/pdf?id=H1lNPxHKDH

Cite this

@inproceedings{a5c5243f6fd14416aca80c4742aeb6b8,

title = "A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case",

abstract = "We give a tight characterization of the (vectorized Euclidean) norm of weights required to realize a function as a single hidden-layer ReLU network with an unbounded number of units (infinite width), extending the univariate characterization of Savarese et al. (2019) to the multivariate case.",

author = "Greg Ongie and Rebecca Willett and Daniel Soudry and Nathan Srebro",

note = "Publisher Copyright: {\textcopyright} 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.; 8th International Conference on Learning Representations, ICLR 2020 ; Conference date: 30-04-2020",

year = "2020",

language = "الإنجليزيّة",

booktitle = "8th International Conference on Learning Representations, ICLR 2020",

}

TY - GEN

T1 - A Function Space View of Bounded Norm Infinite Width ReLU Nets

T2 - 8th International Conference on Learning Representations, ICLR 2020

AU - Ongie, Greg

AU - Willett, Rebecca

AU - Soudry, Daniel

AU - Srebro, Nathan

PY - 2020

Y1 - 2020

N2 - We give a tight characterization of the (vectorized Euclidean) norm of weights required to realize a function as a single hidden-layer ReLU network with an unbounded number of units (infinite width), extending the univariate characterization of Savarese et al. (2019) to the multivariate case.

AB - We give a tight characterization of the (vectorized Euclidean) norm of weights required to realize a function as a single hidden-layer ReLU network with an unbounded number of units (infinite width), extending the univariate characterization of Savarese et al. (2019) to the multivariate case.

UR - http://www.scopus.com/inward/record.url?scp=85150661151&partnerID=8YFLogxK

M3 - منشور من مؤتمر

BT - 8th International Conference on Learning Representations, ICLR 2020

Y2 - 30 April 2020

ER -

A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case

Abstract

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this