62 citations · 423 across the 54 of their papers we have counts for
12 papers · 1 filter
-LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning
Yanwei Fu, Donghao Li, Xinwei Sun +3
This paper proposes a novel Stochastic Split Linearized Bregman Iteration (-LBI) algorithm to efficiently train the deep network. The -LBI introduces an iterative reg…
A Unified Dynamic Approach to Sparse Model Selection
Chendi Huang, Yuan Yao
Sparse model selection is ubiquitous from linear regression to graphical models where regularization paths, as a family of estimators upon the regularization parameter varying, are…
Robust Estimation and Generative Adversarial Nets
Chao Gao, Jiyi Liu, Yuan Yao +1
Robust estimation under Huber's -contamination model has become an important topic in statistics and theoretical computer science. Statistically optimal procedures such as Tukey…
A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training
Tim Tsz-Kit Lau, Jinshan Zeng, Baoyuan Wu +1
Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most…
HodgeRank with Information Maximization for Crowdsourced Pairwise Ranking Aggregation
Qianqian Xu, Jiechao Xiong, Xi Chen +2
Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains. However, task requester usually has a limited amount…
Stochastic Non-convex Ordinal Embedding with Stabilized Barzilai-Borwein Step Size
Ke Ma, Jinshan Zeng, Jiechao Xiong +4
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are batch methods…