3.7k citations · 8k across the 129 of their papers we have counts for
16 papers · 1 filter
Lifted Proximal Operator Machines
Jia Li, Cong Fang, Zhouchen Lin
We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forwa…
Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution
Zhisheng Zhong, Tiancheng Shen, Yibo Yang +2
Convolutional neural networks (CNNs) have recently achieved great success in single-image super-resolution (SISR). However, these methods tend to produce over-smoothed outputs and…
Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
Fanhua Shang, James Cheng, Yuanyuan Liu +2
The heavy-tailed distributions of corrupted outliers and singular values of all channels in low-level vision have proven effective priors for many applications such as background m…
Optimization Algorithm Inspired Deep Neural Network Structure Design
Huan Li, Yibo Yang, Dongmin Chen +1
Deep neural networks have been one of the dominant machine learning approaches in recent years. Several new network structures are proposed and have better performance than the tra…
Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters
Huan Li, Cong Fang, Wotao Yin +1
In this paper, we study the communication and (sub)gradient computation costs in distributed optimization and give a sharp complexity analysis for the proposed distributed accelera…
On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems
Risheng Liu, Shichao Cheng, Yi He +3
Numerous tasks at the core of statistics, learning and vision areas are specific cases of ill-posed inverse problems. Recently, learning-based (e.g., deep) iterative methods have b…