3 papers
math.OC2024
A unified Euler--Lagrange system for analyzing continuous-time accelerated gradient methods
Mitsuru Toyoda, Akatsuki Nishioka, Mirai Tanaka
This paper presents an Euler--Lagrange system for a continuous-time model of the accelerated gradient methods in smooth convex optimization and proposes an associated Lyapunov-func…
math.OC2023
Convergence Rate Analysis of Continuous- and Discrete-Time Smoothing Gradient Algorithms
Mitsuru Toyoda, Akatsuki Nishioka, Mirai Tanaka
This paper addresses the gradient flow -- the continuous-time representation of the gradient method -- with the smooth approximation of a non-differentiable objective function and…
math.OC2023
On a minimization problem of the maximum generalized eigenvalue: properties and algorithms
Akatsuki Nishioka, Mitsuru Toyoda, Mirai Tanaka +1
We study properties and algorithms of a minimization problem of the maximum generalized eigenvalue of symmetric-matrix-valued affine functions, which is nonsmooth and quasiconvex,…