
CoRe: An Efficient Coarserefined Training Framework for BERT
In recent years, BERT has made significant breakthroughs on many natural...
read it

Deep Neural Network Test Coverage: How Far Are We?
DNN testing is one of the most effective methods to guarantee the qualit...
read it

Deep Neural Networks with Short Circuits for Improved Gradient Learning
Deep neural networks have achieved great success both in computer vision...
read it

Fast algorithms for robust principal component analysis with an upper bound on the rank
The robust principal component analysis (RPCA) decomposes a data matrix ...
read it

A Novel Regularization Based on the Error Function for Sparse Recovery
Regularization plays an important role in solving illposed problems by ...
read it

Variational Asymptotic Preserving Scheme for the VlasovPoissonFokkerPlanck System
We design a variational asymptotic preserving scheme for the VlasovPois...
read it

Linear Convergent Decentralized Optimization with Compression
Communication compression has been extensively adopted to speed up large...
read it

Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
Convolutional Neural Networks (CNN) have gained great success in many ar...
read it

A MultiAgent PrimalDual Strategy for Composite Optimization over Distributed Features
This work studies multiagent sharing optimization problems with the obj...
read it

PALM: Pretraining an Autoencoding Autoregressive Language Model for Contextconditioned Generation
Selfsupervised pretraining has emerged as a powerful technique for nat...
read it

Computing the 2adic complexity of two classes of DingHelleseth generalized cyclotomic sequences of period of twin prime products
This paper contributes to compute 2adic complexity of two classes of Di...
read it

Manifold Denoising by Nonlinear Robust Principal Component Analysis
This paper extends robust principal component analysis (RPCA) to nonline...
read it

A Double Residual Compression Algorithm for Efficient Distributed Learning
Largescale machine learning models are often trained by parallel stocha...
read it

Symmetric Regularization based BERT for Pairwise Semantic Reasoning
The ability of semantic reasoning over the sentence pair is essential fo...
read it

Incorporating External Knowledge into Machine Reading for Generative Question Answering
Commonsense and background knowledge is required for a QA model to answe...
read it

StructBERT: Incorporating Language Structures into Pretraining for Deep Language Understanding
Recently, the pretrained language model, BERT (Devlin et al.(2018)Devli...
read it

Incorporating Relation Knowledge into Commonsense Reading Comprehension with Multitask Learning
This paper focuses on how to take advantage of external relational knowl...
read it

On linear convergence of two decentralized algorithms
Decentralized algorithms solve multiagent problems over a connected net...
read it

Multigranularity hierarchical attention fusion networks for reading comprehension and question answering
This paper describes a novel hierarchical attention network for reading ...
read it

A Deep Cascade Model for MultiDocument Reading Comprehension
A fundamental tradeoff between effectiveness and efficiency needs to be...
read it

Fast Signal Recovery from Saturated Measurements by Linear Loss and Nonconvex Penalties
Sign information is the key to overcoming the inevitable saturation erro...
read it

D^2: Decentralized Training over Decentralized Data
While training a machine learning model using multiple workers, each of ...
read it

A primaldual algorithm with optimal stepsizes and its application in decentralized consensus optimization
We consider a primaldual algorithm for minimizing f(x)+h(Ax) with diffe...
read it

Ensemble Methods for Personalized ECommerce Search Challenge at CIKM Cup 2016
Personalized search has been a hot research topic for many years and has...
read it

Exploring Outliers in Crowdsourced Ranking for QoE
Outlier detection is a crucial part of robust evaluation for crowdsource...
read it

Nonconvex penalties with analytical solutions for onebit compressive sensing
Onebit measurements widely exist in the real world, and they can be use...
read it

A decentralized proximalgradient method with network independent stepsizes and separated convergence rates
This paper considers the problem of decentralized optimization with a co...
read it

Mixed onebit compressive sensing with applications to overexposure correction for CT reconstruction
When a measurement falls outside the quantization or measurable range, i...
read it

Coordinate Friendly Structures, Algorithms and Applications
This paper focuses on coordinate update methods, which are useful for so...
read it

ARock: an Algorithmic Framework for Asynchronous Parallel Coordinate Updates
Finding a fixed point to a nonexpansive operator, i.e., x^*=Tx^*, abstra...
read it

Pinball Loss Minimization for Onebit Compressive Sensing
The onebit quantization can be implemented by one single comparator, wh...
read it

A Multiphase Image Segmentation Based on Fuzzy Membership Functions and L1norm Fidelity
In this paper, we propose a variational multiphase image segmentation mo...
read it

The Continuity of Images by Transmission Imaging Revisited
Transmission imaging, as an important imaging technique widely used in a...
read it

Restoration of Images Corrupted by Impulse Noise and Mixed Gaussian Impulse Noise using Blind Inpainting
This article studies the problem of image restoration of observed images...
read it
Ming Yan
is this you? claim profile
Assistant Professor, Department of Computational Mathematics, Science and Engineering; Department of Mathematics at Michigan State University