output
20112022
most citedFederated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks

229 citations

17 papers

cs.IT2022★ 1 cited

Perfect Reconstruction Two-Channel Filter Banks on Arbitrary Graphs

Junxia You, Lihua Yang

This paper extends the existing theory of perfect reconstruction two-channel filter banks from bipartite graphs to non-bipartite graphs. By generalizing the concept of downsampling…

eess.SP2022★ 1 cited

Spline-Like Wavelet Filterbanks with Perfect Reconstruction on Arbitrary Graphs

Junxia You, Lihua Yang

In this work, we propose a class of spline-like wavelet filterbanks for graph signals. These filterbanks possess the properties of critical sampling and perfect reconstruction. Bes…

cs.LG2021★ 17 cited

BROADCAST: Reducing Both Stochastic and Compression Noise to Robustify Communication-Efficient Federated Learning

Heng Zhu, Qing Ling

Communication between workers and the master node to collect local stochastic gradients is a key bottleneck in a large-scale federated learning system. Various recent works have pr…

math.OC2020★ 31 cited

Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?

Kun Yuan, Wei Xu, Qing Ling

In this paper, we consider the decentralized dynamic optimization problem defined over a multi-agent network. Each agent possesses a time-varying local objective function, and all…

cs.LG2019★ 229 cited

Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks

Zhaoxian Wu, Qing Ling, Tianyi Chen +1

This paper deals with distributed finite-sum optimization for learning over networks in the presence of malicious Byzantine attacks. To cope with such attacks, most resilient appro…

math.OC2019★ 35 cited

Communication-Censored Linearized ADMM for Decentralized Consensus Optimization

Weiyu Li, Yaohua Liu, Zhi Tian +1

In this paper, we propose a communication- and computation-efficient algorithm to solve a convex consensus optimization problem defined over a decentralized network. A remarkable e…

cs.DM2019★ 7 cited

A new record of graph enumeration enabled by parallel processing

Zhipeng Xu, Xiaolong Huang, Fabian Jimenez +1

Using three supercomputers, we broke a record set in 2011, in the enumeration of non-isomorphic regular graphs by expanding the sequence of A006820 in Online Encyclopedia of Intege…

cs.CL2019★ 144 cited

Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings

Zhaoning Li, Qi Li, Xiaotian Zou +1

Causality extraction from natural language texts is a challenging open problem in artificial intelligence. Existing methods utilize patterns, constraints, and machine learning tech…

math.NA2018★ 22 cited

Hessian recovery based finite element methods for the Cahn-Hilliard Equation

Minqiang Xu, Hailong Guo, Qingsong Zou

In this paper, we propose a novel recovery based finite element method for the Cahn-Hilliard equation. One distinguishing feature of the method is that we discretize the fourth-ord…

math.NA2018

Computing Integrals Involved the Gaussian Function with a Small Standard Deviation

Yunyun Ma, Yuesheng Xu

We develop efficient numerical integration methods for computing an integral whose integrand is a product of a smooth function and the Gaussian function with a small standard devia…

cs.CV2016★ 198 cited

An Enhanced Deep Feature Representation for Person Re-identification

Shangxuan Wu, Ying-Cong Chen, Xiang Li +3

Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand…

cs.CV2016★ 27 cited

Top-push Video-based Person Re-identification

Jinjie You, Ancong Wu, Xiang Li +1

Most existing person re-identification (re-id) models focus on matching still person images across disjoint camera views. Since only limited information can be exploited from still…

math.OC2016

Two-step Fixed-point proximity algorithms for multi-block separable convex problems

Qia Li, Yuesheng Xu, Na Zhang

Multi-block separable convex problems recently received considerable attention. This class of optimization problems minimizes a separable convex objective function with linear cons…

math.NA2015★ 3 cited

Computing Highly Oscillatory Integrals

Yunyun Ma, Yuesheng Xu

We develop two classes of composite moment-free numerical quadratures for computing highly oscillatory integrals having integrable singularities and stationary points. The first cl…

math.NA2015

Two-parameter regularization of ill-posed spherical pseudo-differential equations in the space of continuous functions

Hui Cao, Sergei V. Pereverzyev, Ian H. Sloan +1

In this paper, a two-step regularization method is used to solve an ill-posed spherical pseudo-differential equation in the presence of noisy data. For the first step of regulariza…

math.FA2011★ 2 cited

Vector-valued Reproducing Kernel Banach Spaces with Applications to Multi-task Learning

Haizhang Zhang, Jun Zhang

Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the…

stat.ML2011★ 55 cited

Reproducing Kernel Banach Spaces with the l1 Norm

Guohui Song, Haizhang Zhang, Fred J. Hickernell

Targeting at sparse learning, we construct Banach spaces B of functions on an input space X with the properties that (1) B possesses an l1 norm in the sense that it is isometricall…