activity
20182022
most citedApproximated Orthonormal Normalisation in Training Neural Networks

2 citations · 2 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG2022

Communication Compression for Decentralized Learning with Operator Splitting Methods

Yuki Takezawa, Kenta Niwa, Makoto Yamada

In decentralized learning, operator splitting methods using a primal-dual formulation (e.g., the Edge-Consensus Learning (ECL)) has been shown to be robust to heterogeneous data an…

cs.DC2021

Revisiting the Primal-Dual Method of Multipliers for Optimisation over Centralised Networks

Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn

The primal-dual method of multipliers (PDMM) was originally designed for solving a decomposable optimisation problem over a general network. In this paper, we revisit PDMM for opti…

cs.LG20192 cited

Approximated Orthonormal Normalisation in Training Neural Networks

Guoqiang Zhang, Kenta Niwa, W. B. Kleijn

Generalisation of a deep neural network (DNN) is one major concern when employing the deep learning approach for solving practical problems. In this paper we propose a new techniqu…

cs.LG2019

Rapidly Adapting Moment Estimation

Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn

Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the indiv…

stat.ML2018

DNN-based Source Enhancement to Increase Objective Sound Quality Assessment Score

Yuma Koizumi, Kenta Niwa, Yusuke Hioka +2

We propose a training method for deep neural network (DNN)-based source enhancement to increase objective sound quality assessment (OSQA) scores such as the perceptual evaluation o…

math.OC2018

Bregman Monotone Operator Splitting

Kenta Niwa, W. Bastiaan Kleijn

Monotone operator splitting is a powerful paradigm that facilitates parallel processing for optimization problems where the cost function can be split into two convex functions. We…