198 citations · 480 across the 36 of their papers we have counts for
36 papers
Variable-preconditioned transformed primal-dual method for generalized Wasserstein Gradient Flows
Jin Zeng, Dawei Zhan, Ruchi Guo +1
We propose a Variable-Preconditioned Transformed Primal-Dual (VPTPD) method for solving generalized Wasserstein gradient flows based on the structure-preserving JKO scheme. This is…
SGCE-Font: Skeleton Guided Channel Expansion for Chinese Font Generation
Jie Zhou, Yefei Wang, Yiyang Yuan +2
The automatic generation of Chinese fonts is an important problem involved in many applications. The predominated methods for the Chinese font generation are based on the deep gene…
StrokeGAN+: Few-Shot Semi-Supervised Chinese Font Generation with Stroke Encoding
Jinshan Zeng, Yefei Wang, Qi Chen +3
The generation of Chinese fonts has a wide range of applications. The currently predominated methods are mainly based on deep generative models, especially the generative adversari…
STAR: Zero-Shot Chinese Character Recognition with Stroke- and Radical-Level Decompositions
Jinshan Zeng, Ruiying Xu, Yu Wu +2
Zero-shot Chinese character recognition has attracted rising attention in recent years. Existing methods for this problem are mainly based on either certain low-level stroke-based…
A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game
Ke Ma, Qianqian Xu, Jinshan Zeng +3
Rank aggregation with pairwise comparisons has shown promising results in elections, sports competitions, recommendations, and information retrieval. However, little attention has…
Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting
Yunxin Liu, Qiaosi Yi, Jinshan Zeng
The lightweight crowd counting models, in particular knowledge distillation (KD) based models, have attracted rising attention in recent years due to their superiority on computati…
CodeGen-Test: An Automatic Code Generation Model Integrating Program Test Information
Maosheng Zhong, Gen Liu, Hongwei Li +3
Automatic code generation is to generate the program code according to the given natural language description. The current mainstream approach uses neural networks to encode natura…
Poisoning Attack against Estimating from Pairwise Comparisons
Ke Ma, Qianqian Xu, Jinshan Zeng +2
As pairwise ranking becomes broadly employed for elections, sports competitions, recommendations, and so on, attackers have strong motivation and incentives to manipulate the ranki…
StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding
Jinshan Zeng, Qi Chen, Yunxin Liu +2
The generation of stylish Chinese fonts is an important problem involved in many applications. Most of existing generation methods are based on the deep generative models, particul…
Moreau Envelope Augmented Lagrangian Method for Nonconvex Optimization with Linear Constraints
Jinshan Zeng, Wotao Yin, Ding-Xuan Zhou
The augmented Lagrangian method (ALM) is one of the most useful methods for constrained optimization. Its convergence has been well established under convexity assumptions or smoot…
On Stochastic Variance Reduced Gradient Method for Semidefinite Optimization
Jinshan Zeng, Yixuan Zha, Ke Ma +1
The low-rank stochastic semidefinite optimization has attracted rising attention due to its wide range of applications. The nonconvex reformulation based on the low-rank factorizat…
DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths
Yanwei Fu, Chen Liu, Donghao Li +3
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error. Howe…
Fully-Corrective Gradient Boosting with Squared Hinge: Fast Learning Rates and Early Stopping
Jinshan Zeng, Min Zhang, Shao-Bo Lin
Boosting is a well-known method for improving the accuracy of weak learners in machine learning. However, its theoretical generalization guarantee is missing in literature. In this…
Fast Stochastic Ordinal Embedding with Variance Reduction and Adaptive Step Size
Ke Ma, Jinshan Zeng, Qianqian Xu +3
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are based on semi…
Fast Polynomial Kernel Classification for Massive Data
Jinshan Zeng, Minrun Wu, Shao-Bo Lin +1
In the era of big data, it is desired to develop efficient machine learning algorithms to tackle massive data challenges such as storage bottleneck, algorithmic scalability, and in…
Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces
Yanwei Fu, Chen Liu, Donghao Li +4
The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite…
On ADMM in Deep Learning: Convergence and Saturation-Avoidance
Jinshan Zeng, Shao-Bo Lin, Yuan Yao +1
In this paper, we develop an alternating direction method of multipliers (ADMM) for deep neural networks training with sigmoid-type activation functions (called \textit{sigmoid-ADM…
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…
Global Convergence of Block Coordinate Descent in Deep Learning
Jinshan Zeng, Tim Tsz-Kit Lau, Shaobo Lin +1
Deep learning has aroused extensive attention due to its great empirical success. The efficiency of the block coordinate descent (BCD) methods has been recently demonstrated in dee…
Finding Global Optima in Nonconvex Stochastic Semidefinite Optimization with Variance Reduction
Jinshan Zeng, Ke Ma, Yuan Yao
There is a recent surge of interest in nonconvex reformulations via low-rank factorization for stochastic convex semidefinite optimization problem in the purpose of efficiency and…
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…
Learning rates for classification with Gaussian kernels
Shao-Bo Lin, Jinshan Zeng, Xiangyu Chang
This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some lo…
A Fast Proximal Gradient Algorithm for Decentralized Composite Optimization over Directed Networks
Jinshan Zeng, Tao He, Mingwen Wang
This paper proposes a fast decentralized algorithm for solving a consensus optimization problem defined in a directed networked multi-agent system, where the local objective functi…
On Nonconvex Decentralized Gradient Descent
Jinshan Zeng, Wotao Yin
Consensus optimization has received considerable attention in recent years. A number of decentralized algorithms have been proposed for {convex} consensus optimization. However, to…