11 citations · 26 across the 8 of their papers we have counts for
11 papers
Accelerated Bregman Proximal Gradient Methods from Dual Geometric Perspectives
Yuya Yamashita, Shota Takahashi, Akiko Takeda
We study Bregman proximal gradient (BPG) algorithms under relative smoothness for convex, relatively strongly convex, and nonconvex objectives. Existing accelerated BPG algorithms…
Beyond Polytopes: Damped Newton Frank--Wolfe Methods over Compact Convex Sets
Shota Takahashi, Akiko Takeda
We study convex optimization over compact convex sets for twice differentiable objective functions with positive definite Hessians, assuming access to the feasible set through a li…
Linesearch-Free Nonlinearly Preconditioned GD with Semiautomatic Geometry Design
Daiki Iwade, Shota Takahashi, Akiko Takeda
Nonlinear preconditioning makes it possible to adapt gradient updates to the growth of the objective's curvature, but combining its design with suitable stepsize selection is chall…
Dynamic Competition of Fast and Collisional Neutrino Flavor Instabilities with Collisional Damping in Spatially Inhomogeneous Systems
Shota Takahashi, Hiroki Nagakura, Masamichi Zaizen +2
Neutrino flavor evolution in dense astrophysical environments such as core-collapse supernova (CCSN) is influenced by collective effects. While the Fast Flavor Instability (FFI) an…
Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration
Shota Takahashi
We study convex optimization problems over a compact convex set where projections are expensive but a linear minimization oracle (LMO) is available. We propose the adaptive conditi…
Approximate Bregman proximal gradient algorithm with variable metric Armijo line search
Kiwamu Fujiki, Shota Takahashi, Akiko Takeda
We propose a variant of the approximate Bregman proximal gradient (ABPG) algorithm for minimizing the sum of a smooth nonconvex function and a nonsmooth convex function. ABPG is kn…
Fast Frank--Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
Shota Takahashi, Sebastian Pokutta, Akiko Takeda
We propose Frank--Wolfe (FW) algorithms with an adaptive Bregman step-size strategy for smooth adaptable (also called: relatively smooth) (weakly-) convex functions. This means tha…
Majorization-minimization Bregman proximal gradient algorithms for NMF with the Kullback--Leibler divergence
Shota Takahashi, Mirai Tanaka, Shiro Ikeda
Nonnegative matrix factorization (NMF) is a popular method in machine learning and signal processing to decompose a given nonnegative matrix into two nonnegative matrices. In this…
Approximate Bregman Proximal Gradient Algorithm for Relatively Smooth Nonconvex Optimization
Shota Takahashi, Akiko Takeda
In this paper, we propose the approximate Bregman proximal gradient algorithm (ABPG) for solving composite nonconvex optimization problems. ABPG employs a new distance that approxi…
Blind Deconvolution with Non-smooth Regularization via Bregman Proximal DCAs
Shota Takahashi, Mirai Tanaka, Shiro Ikeda
Blind deconvolution is a technique to recover an original signal without knowing a convolving filter. It is naturally formulated as a minimization of a quartic objective function u…
New Bregman proximal type algorithms for solving DC optimization problems
Shota Takahashi, Mituhiro Fukuda, Mirai Tanaka
Difference of Convex (DC) optimization problems have objective functions that are differences between two convex functions. Representative ways of solving these problems are the pr…