Eigenvalue Analysis of Hessian Matrices in Quadratic Loss Functions for Machine Learning Optimization
Quadratic functions are fundamental to understand optimization landscapes in machine learning. In this study, we focus on the optimization of a class of quadratic loss functions, examining their behavior through the construction of Hessian matrices and the analysis of their eigenvalues.
Authors
- T. V. N. Prasanna
- A. V. Ramakrishna
- Nathan Sairam
Publication Details
- Journal
- International journal of mathematics and computer science
- Published
- 2025-01-01
- DOI
- https://doi.org/10.69793/ijmcs/03.2025/ramakrishna
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00