Function Space and Critical Points of Linear Convolutional Networks-Reference-Cited by-同舟云学术

Function Space and Critical Points of Linear Convolutional Networks

Published:2024-05-21 Issue:2 Volume:8 Page:333-362
ISSN:2470-6566
Container-title:SIAM Journal on Applied Algebra and Geometry
language:en
Short-container-title:SIAM J. Appl. Algebra Geometry

Author:

Kohn Kathlén¹,Montúfar Guido²,Shahverdi Vahid¹,Trager Matthew³

Affiliation:

1. Department of Mathematics, KTH Royal Institute of Technology, Stockholm, 10044, Sweden.

2. Departments of Mathematics and Statistics, UCLA, Los Angeles, CA 90095 USA, and Max Planck Institute for Mathematics in the Sciences, Leipzig, 04103, Germany.

3. Amazon AWS AI Labs, New York, NY, USA. Work done outside of Amazon.

Funder

Deutsche Forschungsgemeinschaft SPP 2298

European Research Council (ERC) Starting Grant

Bundesministerium für Bildung und Forschung

Knut och Alice Wallenbergs Stiftelse

National Science Foundation

Publisher

Society for Industrial & Applied Mathematics (SIAM)

Reference14 articles.

1. P. Baldi, Linear learning: Landscapes and algorithms, in Advances in Neural Information Processing Systems 1, D. S. Touretzky, ed. Morgan-Kaufmann, 1989, pp. 65–72.

2. Learning in linear neural networks: a survey

3. Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers

4. Advances in Neural Information Processing Systems 34;Dai Z.,2021

5. S. Gunasekar, J. D. Lee, D. Soudry, and N. Srebro, Implicit bias of gradient descent on linear convolutional networks, in Advances in Neural Information Processing Systems 31, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, eds. Curran Associates, 2018, pp. 9461–9471.