Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA) 
Carvalho, L., Costa, J. L., Mourão, J. & Oliveira, G. (2025). The positivity of the neural tangent kernel. SIAM Journal on Mathematics of Data Science. 7 (2), 495-515
Exportar Referência (IEEE) 
L. C. Carvalho et al.,  "The positivity of the neural tangent kernel", in SIAM Journal on Mathematics of Data Science, vol. 7, no. 2, pp. 495-515, 2025
Exportar BibTeX 
@article{carvalho2025_1765952710207,
	author = "Carvalho, L. and Costa, J. L. and Mourão, J. and Oliveira, G.",
	title = "The positivity of the neural tangent kernel",
	journal = "SIAM Journal on Mathematics of Data Science",
	year = "2025",
	volume = "7",
	number = "2",
	doi = "10.1137/24M1659534",
	pages = "495-515",
	url = "https://epubs.siam.org/journal/sjmdaq"
}
Exportar RIS 
TY  - JOUR
TI  - The positivity of the neural tangent kernel
T2  - SIAM Journal on Mathematics of Data Science
VL  - 7
IS  - 2
AU  - Carvalho, L.
AU  - Costa, J. L.
AU  - Mourão, J.
AU  - Oliveira, G.
PY  - 2025
SP  - 495-515
SN  - 2577-0187
DO  - 10.1137/24M1659534
UR  - https://epubs.siam.org/journal/sjmdaq
AB  - The Neural tangent kernel (NTK) has emerged as a fundamental concept in the study of wide neural networks. In particular, it is known that the positivity of the NTK is directly related to the memorization capacity of sufficiently wide networks, i.e., to the possibility of reaching zero loss in training via gradient descent. Here we will improve on previous works and obtain a sharp result concerning the positivity of the NTK of feedforward networks of any depth. More precisely, we will show that, for any nonpolynomial activation function, the NTK is strictly positive definite. Our results are based on a novel characterization of polynomial functions, which is of independent interest.
ER  -