all AI news
HesScale: Scalable Computation of Hessian Diagonals. (arXiv:2210.11639v1 [cs.LG])
Oct. 24, 2022, 1:11 a.m. | Mohamed Elsayed, A. Rupam Mahmood
cs.LG updates on arXiv.org arxiv.org
Second-order optimization uses curvature information about the objective
function, which can help in faster convergence. However, such methods typically
require expensive computation of the Hessian matrix, preventing their usage in
a scalable way. The absence of efficient ways of computation drove the most
widely used methods to focus on first-order approximations that do not capture
the curvature information. In this paper, we develop HesScale, a scalable
approach to approximating the diagonal of the Hessian matrix, to incorporate
second-order information in …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Principal Data Engineer
@ RS21 | Remote
SQL/Power BI Developer
@ ICF | Virginia Remote Office (VA99)
Senior Machine Learning Engineer (Canada Remote)
@ Fullscript | Ottawa, ON
Software Engineer - MLOps.
@ Renesas Electronics | Toyosu, Japan
Junior Data Scientist / Artificial Intelligence consultant
@ Deloitte | Luxembourg, LU