Assembly and iteration: Transition to linearity of wide neural networks
- 8 December 2025
- journal article
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 82
Abstract
No abstract availableFunding Information
- Office of Naval Research
- US Naval Research Laboratory
- National Science Foundation (CCF-2112665)
- Simons Foundation (814639)
- Simons Foundation (DMS-2031883)
This publication has 7 references indexed in Scilit:
- Loss landscapes and optimization in over-parameterized non-linear systems and neural networksApplied and Computational Harmonic Analysis, 2022
- Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical PerspectiveNeural Computation, 2020
- Toward Moderate Overparameterization: Global Convergence Guarantees for Training Shallow Neural NetworksIEEE Journal on Selected Areas in Information Theory, 2020
- Gradient descent optimizes over-parameterized deep ReLU networksMachine Learning, 2019
- Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual NetworksNeural Computation, 2019
- Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural NetworksIEEE Transactions on Information Theory, 2018
- On Riemannian manifolds admitting a function whose gradient is of constant normKodai Mathematical Journal, 1996