9 papers
Adaptive Normalized Gradient Method for -smooth Problems: Estimating Problem Parameters as a Region
Rikiya Okazaki, Shotaro Yagishita, Hideitsu Hino
We propose a parameter-free and efficient gradient descent algorithm for -smooth optimization. This notion of smoothness, introduced by Zhang et al. (2020), allows the s…
A proximal gradient method with adaptive backtracking for weakly smooth multiobjective optimization
Yuki Miyazaki, Masaru Ito, Shotaro Yagishita
In this paper, we propose a proximal gradient method with adaptive linesearch for multiobjective optimization problems whose objective functions are weakly smooth, i.e., they have…
Simple linesearch-free first-order methods for nonconvex optimization
Shotaro Yagishita, Masaru Ito
This paper presents an auto-conditioned proximal gradient method for nonconvex optimization. The method determines the stepsize using an estimation of local curvature and does not…
Convergence of linesearch-based generalized conditional gradient methods without smoothness assumptions
Shotaro Yagishita
The generalized conditional gradient method is a popular algorithm for solving composite problems whose objective function is the sum of a smooth function and a nonsmooth convex fu…
Proximal gradient-type method with generalized distance and convergence analysis without global descent lemma
Shotaro Yagishita, Masaru Ito
We consider solving nonconvex composite optimization problems in which the sum of a smooth function and a nonsmooth function is minimized. Many of convergence analyses of proximal…
Optimal reinsurance and investment via stochastic projected gradient method based on Malliavin calculus
Yuta Otsuki, Shotaro Yagishita
This paper proposes a new approach using the stochastic projected gradient method and Malliavin calculus for optimal reinsurance and investment strategies. Unlike traditional metho…
Fast algorithm for sparse least trimmed squares via trimmed-regularized reformulation
Shotaro Yagishita
The least trimmed squares (LTS) is a reasonable formulation of robust regression whereas it suffers from high computational cost due to the nonconvexity and nonsmoothness of its ob…
Proximal Diagonal Newton Methods for Composite Optimization Problems
Shotaro Yagishita, Shummin Nakayama
This paper proposes new proximal Newton-type methods with a diagonal metric for solving composite optimization problems whose objective function is the sum of a twice continuously…
Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
Akifumi Okuno, Shotaro Yagishita
In this study, we tackle the challenge of outlier-robust predictive modeling using highly expressive neural networks. Our approach integrates two key components: (1) a transformed…