An Exact Kernel Equivalence for Finite Classification Models

Autor:	Bell, Brian, Geyer, Michael, Glickenstein, David, Fernandez, Amanda, Moore, Juston
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning F.2 G.1
Druh dokumentu:	Working Paper
Popis:	We explore the equivalence between neural networks and kernel methods by deriving the first exact representation of any finite-size parametric classification model trained with gradient descent as a kernel machine. We compare our exact representation to the well-known Neural Tangent Kernel (NTK) and discuss approximation error relative to the NTK and other non-exact path kernel formulations. We experimentally demonstrate that the kernel can be computed for realistic networks up to machine precision. We use this exact kernel to show that our theoretical contribution can provide useful insights into the predictions made by neural networks, particularly the way in which they generalize. Comment: TAG-ML at ICML 2023 in Proceedings. 8 pages, 6 figures, proofs in Appendix
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2308.00824 Zobrazit plný text záznamu View this record from Arxiv