5 papers
Accelerated Tensor Completion via Trace-Regularized Fully-Connected Tensor Network
Wenchao Xie, Qingsong Wang, Chengcheng Yan +1
The fully-connected tensor network (FCTN) decomposition has gained prominence in the field of tensor completion owing to its powerful capacity to capture the low-rank characteristi…
Accelerated Proximal Dogleg Majorization for Sparse Regularized Quadratic Optimization Problem
Feifei Zhao, Qingsong Wang, Mingcai Ding +1
This paper addresses the problems of minimizing the sum of a quadratic function and a proximal-friendly nonconvex nonsmooth function. While the existing Proximal Dogleg Opportunist…
Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
Chengcheng Yan, Jiawei Xu, Zheng Peng +1
The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates…
A Triple-Inertial Accelerated Alternating Optimization Method for Deep Learning Training
Chengcheng Yan, Jiawei Xu, Qingsong Wang +1
The stochastic gradient descent (SGD) algorithm has achieved remarkable success in training deep learning models. However, it has several limitations, including susceptibility to v…
Efficient QR-Based CP Decomposition Acceleration via Restructured Dimension Tree and Customized Extrapolation
Wenchao Xie, Jiawei Xu, Zheng Peng +1
The canonical polyadic (CP) decomposition is one of the most widely used tensor decomposition techniques. The conventional CP decomposition algorithm combines alternating least squ…