Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant Updates
Quasi-Newton (qN) techniques approximate the Newton step by estimating the Hessian using the so-called secant equations. Some of these methods compute the Hessian using several secant equations but produce non-symmetric updates. Other quasi-Newton schemes, such as BFGS, enforce symmetry but cannot satisfy more than one secant equation. We propose a new type of quasi-Newton symmetric update using several secant equations in a least-squares sense. Our approach generalizes and unifies the design of quasi-Newton updates and satisfies provable robustness guarantees.
WOS:000659893800062
2021-01-01
Brookline
Proceedings of Machine Learning Research; 130
550
558
REVIEWED
Event name | Event place | Event date |
ELECTR NETWORK | Apr 13-15, 2021 | |