Learn Before
Concept

Convex Function via Hessian Eigenvalues

In multi-dimensional optimization, convex functions are those where the eigenvalues of the Hessian matrix are never negative. While assuming convexity provides a great mathematical tool to study optimization algorithms, most practical deep learning problems do not fall into this category.

0

1

Updated 2026-05-15

Contributors are:

Who are from:

Tags

D2L

Dive into Deep Learning @ D2L

Related