6 papers
A restart-free accelerated algorithm for nonconvex minimization: continuous- and discrete-time analysis
Kansei Ushiyama, Shun Sato
We propose two deterministic momentum-based first-order methods for minimizing lower-bounded nonconvex functions with Lipschitz-continuous gradients and Hessians. Both methods atta…
Essential Convergence Rates of Continuous-Time Models for Optimization Methods
Kansei Ushiyama, Shun Sato, Takayasu Matsuo
Designing and analyzing optimization methods via continuous-time models expressed as ordinary differential equations (ODEs) is a promising approach for its intuitiveness and simpli…
A -accelerated FISTA for composite strongly convex problems
Kansei Ushiyama
In this paper, we propose a novel accelerated forward-backward splitting algorithm for minimizing composite convex functions expressed as the sum of a smooth function and a possibl…
Differentiable Pareto-Smoothed Weighting for High-Dimensional Heterogeneous Treatment Effect Estimation
Yoichi Chikahara, Kansei Ushiyama
There is a growing interest in estimating heterogeneous treatment effects across individuals using their high-dimensional feature attributes. Achieving high performance in such hig…
A new unified framework for designing convex optimization methods with prescribed theoretical convergence estimates: A numerical analysis approach
Kansei Ushiyama, Shun Sato, Takayasu Matsuo
We propose a new unified framework for describing and designing gradient-based convex optimization methods from a numerical analysis perspective. There the key is the new concept o…
Essential convergence rate of ordinary differential equations appearing in optimization
Kansei Ushiyama, Shun Sato, Takayasu Matsuo
Some continuous optimization methods can be connected to ordinary differential equations (ODEs) by taking continuous limits, and their convergence rates can be explained by the ODE…