Skip to Main content Skip to Navigation
New interface
Conference papers

On the Inductive Bias of Neural Tangent Kernels

Alberto Bietti 1 Julien Mairal 1 
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
Abstract : State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain over-parameterized regime, the learning dynamics of gradient descent are governed by a certain kernel obtained at initialization, called the neural tangent kernel. We study the inductive bias of learning in such a regime by analyzing this kernel and the corresponding function space (RKHS). In particular, we study smoothness, approximation, and stability properties of functions with finite norm, including stability to image deformations in the case of convolutional networks, and compare to other known kernels for similar architectures.
Complete list of metadata

Cited literature [56 references]  Display  Hide  Download
Contributor : Alberto Bietti Connect in order to contact the contributor
Submitted on : Friday, October 25, 2019 - 5:40:06 PM
Last modification on : Friday, February 4, 2022 - 3:31:30 AM


Files produced by the author(s)


  • HAL Id : hal-02144221, version 2
  • ARXIV : 1905.12173



Alberto Bietti, Julien Mairal. On the Inductive Bias of Neural Tangent Kernels. NeurIPS 2019 - Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada. pp.12873-12884. ⟨hal-02144221v2⟩



Record views


Files downloads