activity
20182021
most citedConjugate-gradient-based Adam for stochastic optimization and its application to deep learning

5 citations · 5 across the 3 of their papers we have counts for

collaborators

7 papers

math.OC2021

The Number of Steps Needed for Nonconvex Optimization of a Deep Learning Optimizer is a Rational Function of Batch Size

Hideaki Iiduka

Recently, convergence as well as convergence rate analyses of deep learning optimizers for nonconvex optimization have been widely studied. Meanwhile, numerical evaluations for the…

math.OC2020

Riemannian Stochastic Fixed Point Optimization Algorithm

Hideaki Iiduka, Hiroyuki Sakai

This paper considers a stochastic optimization problem over the fixed point sets of quasinonexpansive mappings on Riemannian manifolds. The problem enables us to consider Riemannia…

math.OC2020

Riemannian Adaptive Optimization Algorithm and Its Application to Natural Language Processing

Hiroyuki Sakai, Hideaki Iiduka

This paper proposes a Riemannian adaptive optimization algorithm to optimize the parameters of deep neural networks. The algorithm is an extension of both AMSGrad in Euclidean spac…

math.OC20205 cited

Conjugate-gradient-based Adam for stochastic optimization and its application to deep learning

Yu Kobayashi, Hideaki Iiduka

This paper proposes a conjugate-gradient-based Adam algorithm blending Adam with nonlinear conjugate gradient methods and shows its convergence analysis. Numerical experiments on t…

math.OC2020

Appropriate Learning Rates of Adaptive Learning Rate Optimization Algorithms for Training Deep Neural Networks

Hideaki Iiduka

This paper deals with nonconvex stochastic optimization problems in deep learning and provides appropriate learning rates with which adaptive learning rate optimization algorithms,…

math.OC2020

Hybrid Riemannian Conjugate Gradient Methods with Global Convergence Properties

Hiroyuki Sakai, Hideaki Iiduka

This paper presents new Riemannian conjugate gradient methods and global convergence analyses under the strong Wolfe conditions. The main idea of the new methods is to combine the…