T. Zhang

Publications
Influence

SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator

Cong Fang, C. Li, Zhouchen Lin, T. Zhang
Computer Science, Mathematics
NeurIPS
1 July 2018

In this paper, we propose a new technique named Stochastic Path-Integrated Differential EstimatoR (SPIDER), which can be used to track many deterministic quantities of interest with significantly reduced computational cost. Expand

Deep Subspace Clustering Networks

Pan Ji, T. Zhang, Hongdong Li, M. Salzmann, I. Reid
Computer Science
NIPS
8 September 2017

We present a novel deep neural network architecture to learn (in an unsupervised manner) an explicit non-linear mapping of the data that is well-adapted to subspace clustering. Expand

Deep Learning Based Feature Selection for Remote Sensing Scene Classification

Qin Zou, Lihao Ni, T. Zhang, Q. Wang
Computer Science
IEEE Geoscience and Remote Sensing Letters
18 September 2015

A novel deep-learning-based feature-selection method has been proposed, which formulates the featureselection problem as a feature reconstruction problem in a DBN. Expand

Efficient mini-batch training for stochastic optimization

Mu Li, T. Zhang, Yuqiang Chen, Alex Smola
Computer Science
KDD
24 August 2014

Stochastic gradient descent (SGD) is a popular technique for large-scale optimization problems in machine learning. Expand

Learning to Remember Translation History with a Continuous Cache

Zhaopeng Tu, Y. Liu, Shuming Shi, T. Zhang
Computer Science
TACL
26 November 2017

We propose to augment NMT models with a very light-weight cache-like memory network, which stores recent hidden representations as translation history. Expand

Stochastic Optimization with Importance Sampling for Regularized Loss Minimization

P. Zhao, T. Zhang
Mathematics, Computer Science
ICML
6 July 2015

Uniform sampling of training data has been commonly used in traditional stochastic optimization algorithms such as Proximal Stochastic Mirror Descent (prox-SMD) and prox-SDCA. Expand

Stochastic Optimization with Importance Sampling

P. Zhao, T. Zhang
Mathematics, Computer Science
ArXiv
13 January 2014

In this paper we study stochastic optimization with importance sampling, which improves the convergence rate for prox-SGD and prox-SDCA. Expand

ARGs-OAP: online analysis pipeline for antibiotic resistance genes detection from metagenomic data using an integrated structured ARG-database

Y. Yang, Xiaotao Jiang, +6 authors T. Zhang
Computer Science, Medicine
Bioinform.
1 August 2016

We developed an online pipeline called ARGs-OAP for fast annotation and classification of ARG-like sequences from metagenomic data from environmental samples. Expand

Super-Identity Convolutional Neural Network for Face Hallucination

Kaipeng Zhang, Zhanpeng Zhang, +4 authors T. Zhang
Computer Science
ECCV
8 September 2018

This paper proposes Super-Identity Convolutional Neural Network (SICNN) to recover identity information for generating faces closed to the real identity. Expand

A multistage, multimethod approach for automatic detection and classification of epileptiform EEG

Hesheng Liu, T. Zhang, F. Yang
Computer Science, Medicine
IEEE Transactions on Biomedical Engineering
1 December 2002

An efficient system for detection of epileptic activity in ambulatory electroencephalogram (EEG) that combines multiple signal-processing methods in a multistage scheme, integrating adaptive filtering, wavelet transform, an artificial neural network, and expert system. Expand

Recommended Authors