
MultiTensor Network Representation for HighOrder Tensor Completion
This work studies the problem of highdimensional data (referred to tens...
read it

Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization
Adaptive gradient methods, such as Adam, have achieved tremendous succes...
read it

Understanding the UnderCoverage Bias in Uncertainty Estimation
Estimating the data uncertainty in regression tasks is often done by lea...
read it

Policy Finetuning: Bridging SampleEfficient Offline and Online Reinforcement Learning
Recent theoretical work studies sampleefficient reinforcement learning ...
read it

Evaluating StateoftheArt Classification Models Against Bayes Optimality
Evaluating the inherent difficulty of a given datadriven classification...
read it

Polyjuice: HighPerformance Transactions via Learned Concurrency Control
Concurrency control algorithms are key determinants of the performance o...
read it

Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
Several recent works [40, 24] observed an interesting phenomenon in neur...
read it

Emerging Paradigms of Neural Network Pruning
Overparameterization of neural networks benefits the optimization and g...
read it

SampleEfficient Learning of Stackelberg Equilibria in GeneralSum Games
Real world applications such as economics and policy making often involv...
read it

Localized Calibration: Metrics and Recalibration
Probabilistic classifiers output confidence scores along with their pred...
read it

Don't Just Blame Overparametrization for Overconfidence: Theoretical Analysis of Calibration in Binary Classification
Modern machine learning models with high accuracy are often miscalibrate...
read it

Automatic Segmentation of OrgansatRisk from HeadandNeck CT using Separable Convolutional Neural Network with HardRegionWeighted Loss
Nasopharyngeal Carcinoma (NPC) is a leading form of HeadandNeck (HAN) ...
read it

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
The early phase of training has been shown to be important in two ways f...
read it

Neural Pruning via Growing Regularization
Regularization has long been utilized to learn sparsity in deep neural n...
read it

An Event Correlation Filtering Method for Fake News Detection
Nowadays, social network platforms have been the prime source for people...
read it

Multihead Knowledge Distillation for Model Compression
Several methods of knowledge distillation have been developed for neural...
read it

Knowledge Distillation Thrives on Data Augmentation
Knowledge distillation (KD) is a general deep neural network training fr...
read it

Unsupervised Paraphrase Generation via Dynamic Blocking
We propose Dynamic Blocking, a decoding algorithm which enables largesc...
read it

How Important is the TrainValidation Split in MetaLearning?
Metalearning aims to perform fast adaptation on a new task through lear...
read it

Towards Understanding Hierarchical Learning: Benefits of Neural Representations
Deep neural networks can empirically perform efficient hierarchical lear...
read it

PLVER: Joint Stable Allocation and Content Replication for Edgeassisted Live Video Delivery
The live streaming services have gained extreme popularity in recent yea...
read it

Collaborative Distillation for UltraResolution Universal Style Transfer
Universal style transfer methods typically leverage rich representations...
read it

MNN: A Universal and Efficient Inference Engine
Deploying deep learning models on mobile devices draws more and more att...
read it

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
We introduce a parameterization method called Neural Bayes which allows ...
read it

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
We propose Taylorized training as an initiative towards better understan...
read it

Opposite Structure Learning for Semisupervised Domain Adaptation
Current adversarial adaptation methods attempt to align the crossdomain...
read it

Attentive Student Meets MultiTask Teacher: Improved Knowledge Distillation for Pretrained Models
In this paper, we explore the knowledge distillation approach under the ...
read it

Global Capacity Measures for Deep ReLU Networks via Path Sampling
Classical results on the statistical complexity of linear models have co...
read it

On the Generalization Gap in Reparameterizable Reinforcement Learning
Understanding generalization in reinforcement learning (RL) is a signifi...
read it

Triplet Distillation for Deep Face Recognition
Convolutional neural networks (CNNs) have achieved a great success in fa...
read it

Allocating Limited Resources to Protect a Massive Number of Targets using a Game Theoretic Model
Resource allocation is the process of optimizing the rare resources. In ...
read it

Structured Pruning for Efficient ConvNets via Incremental Regularization
Parameter pruning is a promising approach for CNN compression and accele...
read it

Three Dimensional Convolutional Neural Network Pruning with RegularizationBased Method
In recent years, threedimensional convolutional neural network (3D CNN)...
read it

Identifying Generalization Properties in Neural Networks
While it has not yet been proven, empirical evidence suggests that model...
read it

Structured Deep Neural Network Pruning by Varying Regularization Parameters
Convolutional Neural Networks (CNN's) are restricted by their massive co...
read it

Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
Although deep Convolutional Neural Network (CNN) has shown better perfor...
read it

Exploiting Color Name Space for Salient Object Detection
In this paper, we will investigate the contribution of color names for s...
read it

Synthesizing Training Images for Boosting Human 3D Pose Estimation
Human 3D pose estimation from a single image is a challenging task with ...
read it
Huan Wang
is this you? claim profile