Minimum norm interpolation by perceptra: Explicit regularization and implicit bias

Autor:	Park, Jiyoung, Pelakh, Ian, Wojtowytsch, Stephan
Rok vydání:	2023
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning Mathematics - Optimization and Control
Zdroj:	Thirty-seventh Conference on Neural Information Processing Systems 2023
Druh dokumentu:	Working Paper
Popis:	We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number of data points and parameters tends to infinity when a weight decay regularizer is penalized with a coefficient which vanishes at a precise rate as the network width and the number of data points grow. With and without explicit regularization, we numerically study the implicit bias of common optimization algorithms towards known minimum norm interpolants.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2311.06138 Zobrazit plný text záznamu View this record from Arxiv