Gradient descent on infinitely wide neural networks: global convergence and generalization

DOI10.4171/icm2022/121arXiv2110.08084MaRDI QIDQ6200217

Lénaïc Chizat, Francis Bach

Publication date: 22 March 2024

Published in: International Congress of Mathematicians (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.08084

zbMATH Keywords

neural networksgradient flowmachine learninggradient descentoptimal transport

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical optimization and variational techniques (65K10) Numerical methods based on nonlinear programming (49M37) Probabilistic methods in Banach space theory (46B09) Methods of reduced gradient type (90C52) Probabilistic metric spaces (54E70)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Lectures on convex optimization
• Probabilistic representation and uniqueness results for measure-valued solutions of transport equations
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• Universal approximation bounds for superpositions of a sigmoidal function
• Asymptotic Statistics
• Bounds on rates of variable-basis and neural-network approximation
• An Introduction to Numerical Analysis
• A mean field view of the landscape of two-layer neural networks
• Mean Field Analysis of Neural Networks: A Law of Large Numbers
• Breaking the Curse of Dimensionality with Convex Neural Networks