Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Jin, Qiujiang"'
We propose adaptive, line search-free second-order methods with optimal rate of convergence for solving convex-concave min-max problems. By means of an adaptive step size, our algorithms feature a simple update rule that requires solving only one lin
Externí odkaz:
http://arxiv.org/abs/2406.02016
In this paper, we establish the first explicit and non-asymptotic global convergence analysis of the BFGS method when deployed with an inexact line search scheme that satisfies the Armijo-Wolfe conditions. We show that BFGS achieves a global converge
Externí odkaz:
http://arxiv.org/abs/2404.16731
In this paper, we explore the non-asymptotic global convergence rates of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method implemented with exact line search. Notably, due to Dixon's equivalence result, our findings are also applicable to other quas
Externí odkaz:
http://arxiv.org/abs/2404.01267
Quasi-Newton algorithms are among the most popular iterative methods for solving unconstrained minimization problems, largely due to their favorable superlinear convergence property. However, existing results for these algorithms are limited as they
Externí odkaz:
http://arxiv.org/abs/2302.08580
Statistical and Computational Complexities of BFGS Quasi-Newton Method for Generalized Linear Models
The gradient descent (GD) method has been used widely to solve parameter estimation in generalized linear models (GLMs), a generalization of linear models when the link function can be non-linear. In GLMs with a polynomial link function, it has been
Externí odkaz:
http://arxiv.org/abs/2206.00207
Non-asymptotic analysis of quasi-Newton methods have gained traction recently. In particular, several works have established a non-asymptotic superlinear rate of $\mathcal{O}((1/\sqrt{t})^t)$ for the (classic) BFGS method by exploiting the fact that
Externí odkaz:
http://arxiv.org/abs/2202.10538
Autor:
Jin, Qiujiang, Mokhtari, Aryan
In this paper, we study the application of quasi-Newton methods for solving empirical risk minimization (ERM) problems defined over a large dataset. Traditional deterministic and stochastic quasi-Newton methods can be executed to solve such problems;
Externí odkaz:
http://arxiv.org/abs/2106.05445
Autor:
Jin, Qiujiang, Mokhtari, Aryan
In this paper, we study and prove the non-asymptotic superlinear convergence rate of the Broyden class of quasi-Newton algorithms which includes the Davidon--Fletcher--Powell (DFP) method and the Broyden--Fletcher--Goldfarb--Shanno (BFGS) method. The
Externí odkaz:
http://arxiv.org/abs/2003.13607
Autor:
Jin, Qiujiang1 (AUTHOR) qiujiang@austin.utexas.edu, Mokhtari, Aryan1 (AUTHOR)
Publikováno v:
Mathematical Programming. Jun2023, Vol. 200 Issue 1, p425-473. 49p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.