
DeepSqueeze: Decentralization Meets ErrorCompensated Compression
Communication is a key bottleneck in distributed training. Recently, an ...
read it

DeepSqueeze: Parallel Stochastic Gradient Descent with DoublePass ErrorCompensated Compression
Communication is a key bottleneck in distributed training. Recently, an ...
read it

Optimal Feature Transport for CrossView Image GeoLocalization
This paper addresses the problem of crossview image based localization,...
read it

Estimating and Inferring the Maximum Degree of StimulusLocked TimeVarying Brain Connectivity Networks
Neuroscientists have enjoyed much success in understanding brain functio...
read it

DoubleSqueeze: Parallel Stochastic Gradient Descent with DoublePass ErrorCompensated Compression
A standard approach in large scale machine learning is distributed stoch...
read it

MAP Inference via L2Sphere Linear Program Reformulation
Maximum a posteriori (MAP) inference is an important task for graphical ...
read it

NATTACK: Learning the Distributions of Adversarial Examples for an Improved BlackBox Attack on Deep Neural Networks
Powerful adversarial attack methods are vital for understanding how to c...
read it

Neural Collaborative Subspace Clustering
We introduce the Neural Collaborative Subspace Clustering, a neural mode...
read it

Efficient Decisionbased Blackbox Adversarial Attacks on Face Recognition
Face recognition has obtained remarkable progress in recent years due to...
read it

Dynamic Layer Aggregation for Neural Machine Translation with RoutingbyAgreement
With the promising progress of deep neural networks, layer aggregation h...
read it

Sharp Analysis for Nonconvex SGD Escaping from Saddle Points
In this paper, we prove that the simplest Stochastic Gradient Descent (S...
read it

Tencent MLImages: A LargeScale MultiLabel Image Database for Visual Representation Learning
In existing visual representation learning tasks, deep convolutional neu...
read it

HessianAware ZerothOrder Optimization for BlackBox Adversarial Attack
Zerothorder optimization or derivativefree optimization is an importan...
read it

FiniteSample Analyses for Fully Decentralized MultiAgent Reinforcement Learning
Despite the increasing interest in multiagent reinforcement learning (M...
read it

Crossdatabase nonfrontal facial expression recognition based on transductive deep transfer learning
Crossdatabase nonfrontal expression recognition is a very meaningful b...
read it

Neural Machine Translation with AdequacyOriented Learning
Although Neural Machine Translation (NMT) models have advanced stateof...
read it

SuperIdentity Convolutional Neural Network for Face Hallucination
Face hallucination is a generative task to superresolve the facial imag...
read it

Stochastic PrimalDual Method for Empirical Risk Minimization with O(1) PerIteration Complexity
Regularized empirical risk minimization problem with linear predictor ap...
read it

Scalable Deep kSubspace Clustering
Subspace clustering algorithms are notorious for their scalability issue...
read it

Proximal Gradient Method for Manifold Optimization
This paper considers manifold optimization problems with nonsmooth and n...
read it

MultiHead Attention with Disagreement Regularization
Multihead attention is appealing for the ability to jointly attend to i...
read it

Modeling Localness for SelfAttention Networks
Selfattention networks have proven to be of profound value for its stre...
read it

Exploiting Deep Representations for Neural Machine Translation
Advanced neural machine translation (NMT) models generally implement enc...
read it

Orthogonal Deep Features Decomposition for AgeInvariant Face Recognition
As facial appearance is subject to significant intraclass variations ca...
read it

Modeling Varying CameraIMU Time Offset in OptimizationBased VisualInertial Odometry
Combining cameras and inertial measurement units (IMUs) has been proven ...
read it

Parametrized Deep QNetworks Learning: Reinforcement Learning with DiscreteContinuous Hybrid Action Space
Most existing deep reinforcement learning (DRL) frameworks consider eith...
read it

Fully Implicit Online Learning
Regularized online learning is widely used in machine learning. In this ...
read it

TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game
Starcraft II (SCII) is widely considered as the most challenging Real Ti...
read it

A convex formulation for highdimensional sparse sliced inverse regression
Sliced inverse regression is a popular tool for sufficient dimension red...
read it

Adaptive Sampling Towards Fast Graph Representation Learning
Graph Convolutional Networks (GCNs) have become a crucial tool on learni...
read it

Diffusion Approximations for Online Principal Component Estimation and Global Convergence
In this paper, we propose to adopt the diffusion approximation tools to ...
read it

Endtoend Active Object Tracking and Its Realworld Deployment via Reinforcement Learning
We study active object tracking, where a tracker takes visual observatio...
read it

Video Relocalization
Many methods have been developed to help people find the video contents ...
read it

Recurrent Fusion Network for Image Captioning
Recently, much advance has been made in image captioning, and an encoder...
read it

Unsupervised ImagetoImage Translation with Stacked CycleConsistent Adversarial Networks
Recent studies on unsupervised imagetoimage translation have made rema...
read it

When Work Matters: Transforming Classical Network Structures to Graph CNN
Numerous pattern recognition applications can be formed as learning from...
read it

SPIDER: NearOptimal NonConvex Optimization via Stochastic Path Integrated Differential Estimator
In this paper, we propose a new technique named Stochastic PathIntegrat...
read it

Error Compensated Quantized SGD and its Applications to Largescale Distributed Optimization
Largescale distributed optimization is of great importance in various a...
read it

Safe Element Screening for Submodular Function Minimization
Submodular functions are discrete analogs of convex functions, which hav...
read it

Incorporating PseudoParallel Data for Quantifiable Sequence Editing
In the task of quantifiable sequence editing (QuaSE), a model needs to e...
read it

Finegrained Video Attractiveness Prediction Using Multimodal Deep Learning on a Large Realworld Dataset
Nowadays, billions of videos are online ready to be viewed and shared. A...
read it

Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
The success of current deep saliency detection methods heavily depends o...
read it

Tensor graph convolutional neural network
In this paper, we propose a novel tensor graph convolutional neural netw...
read it

Decentralization Meets Quantization
Optimizing distributed learning systems is an art of balancing between c...
read it

Fully Decentralized MultiAgent Reinforcement Learning with Networked Agents
We consider the problem of fully decentralized multiagent reinforcement...
read it

Composite Functional Gradient Learning of Generative Adversarial Models
Generative adversarial networks (GAN) have become popular for generating...
read it

Translating ProDrop Languages with Reconstruction Models
Pronouns are frequently omitted in prodrop languages, such as Chinese, ...
read it

Learning to Remember Translation History with a Continuous Cache
Existing neural machine translation (NMT) models generally translate sen...
read it

Candidates v.s. Noises Estimation for Large MultiClass Classification Problem
This paper proposes a method for multiclass classification problems, wh...
read it

Gradient Sparsification for CommunicationEfficient Distributed Optimization
Modern large scale machine learning applications require stochastic opti...
read it
Tong Zhang
is this you? claim profile
Machine learning researcher, and the executive director of Tencent AI Lab