
Large Motion Video SuperResolution with Dual Subnet and MultiStage Communicated Upsampling
Video superresolution (VSR) aims at restoring a video in lowresolution...
read it

MWQ: Multiscale Wavelet Quantized Neural Networks
Model quantization can reduce the model size and computational latency, ...
read it

Effective and Fast: A Novel Sequential Single Path Search for MixedPrecision Quantization
Since model quantization helps to reduce the model size and computation ...
read it

Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks
In order to deploy deep convolutional neural networks (CNNs) on resource...
read it

Differentially Private ADMM Algorithms for Machine Learning
In this paper, we study efficient differentially private alternating dir...
read it

Boosting Gradient for WhiteBox Adversarial Attacks
Deep neural networks (DNNs) are playing key roles in various artificial ...
read it

A Single Frame and MultiFrame Joint Network for 360degree Panorama Video SuperResolution
Spherical videos, also known as 360 (panorama) videos, can be viewed wit...
read it

Video Super Resolution Based on Deep Learning: A comprehensive survey
In recent years, deep learning has made great progress in the fields of ...
read it

A Unified Weight Learning and LowRank Regression Model for Robust Face Recognition
Regressionbased error modelling has been extensively studied for face r...
read it

Deep ResidualDense Lattice Network for Speech Enhancement
Convolutional neural networks (CNNs) with residual links (ResNets) and c...
read it

Efficient Relaxed Gradient Support Pursuit for Sparsity Constrained Nonconvex Optimization
Largescale nonconvex sparsityconstrained problems have recently gaine...
read it

signADAM: Learning Confidences for Deep Neural Networks
In this paper, we propose a new firstorder gradientbased algorithm to ...
read it

CUNet: Cascaded UNet with Loss Weighted Sampling for Brain Tumor Segmentation
This paper proposes a novel cascaded UNet for brain tumor segmentation....
read it

MultiPrecision Quantized Neural Networks via Encoding Decomposition of 1 and +1
The training of deep neural networks (DNNs) requires intensive resources...
read it

Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications
The heavytailed distributions of corrupted outliers and singular values...
read it

ASVRG: Accelerated Proximal SVRG
This paper proposes an accelerated proximal stochastic variance reduced ...
read it

A Unified Approximation Framework for Deep Neural Networks
Deep neural networks (DNNs) have achieved significant success in a varie...
read it

A Unified Approximation Framework for NonLinear Deep Neural Networks
Deep neural networks (DNNs) have achieved significant success in a varie...
read it

A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
Recent years have witnessed exciting progress in the study of stochastic...
read it

Tractable and Scalable Schatten QuasiNorm Approximations for Rank Minimization
The Schatten quasinorm was introduced to bridge the gap between the tra...
read it

VRSGD: A Simple Stochastic Variance Reduction Method for Machine Learning
In this paper, we propose a simple variant of the original SVRG, called ...
read it

Guaranteed Sufficient Decrease for Stochastic Variance Reduced Gradient Optimization
In this paper, we propose a novel sufficient decrease technique for stoc...
read it

Accelerated Variance Reduced Stochastic ADMM
Recently, many variance reduced stochastic alternating direction method ...
read it

Larger is Better: The Effect of Learning Rates Enjoyed by Stochastic Optimization with Progressive Variance Reduction
In this paper, we propose a simple variant of the original stochastic va...
read it

Fast Stochastic Variance Reduced Gradient Method with Momentum Acceleration for Machine Learning
Recently, research on accelerated stochastic gradient descent methods (e...
read it

Guaranteed Sufficient Decrease for Variance Reduced Stochastic Gradient Descent
In this paper, we propose a novel sufficient decrease technique for vari...
read it

Scalable Algorithms for Tractable Schatten QuasiNorm Minimization
The Schattenp quasinorm (0<p<1) is usually used to replace the standar...
read it

Unified Scalable Equivalent Formulations for Schatten QuasiNorms
The Schatten quasinorm can be used to bridge the gap between the nuclea...
read it

Regularized Orthogonal Tensor Decompositions for MultiRelational Learning
Multirelational learning has received lots of attention from researcher...
read it

Structured LowRank Matrix Factorization with Missing and Grossly Corrupted Observations
Recovering lowrank and sparse matrices from incomplete or corrupted obs...
read it