2 papers
math.NA2025
Anderson-type acceleration method for Deep Neural Network optimization
Kazufumi Ito, Tiancheng Xue
In this paper we consider the neural network optimization. We develop Anderson-type acceleration method for the stochastic gradient decent method and it improves the network perman…
math.NA2025
Reduced order method based Anderson-type acceleration method for nonlinear least square problems and large scale ill-posed problems
Kazufumi Ito, Tiancheng Xue
In this paper, we propose an acceleration framework for a class of iterative methods using the Reduced Order Method (ROM). Assuming that the underlying iterative scheme generates a…