activity
20122022
most citedHyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning

32 citations · 140 across the 16 of their papers we have counts for

collaborators
Showing 2018 · cs.LGShow all

7 papers · 2 filters

cs.LG2018

ASVRG: Accelerated Proximal SVRG

Fanhua Shang, Licheng Jiao, Kaiwen Zhou +3

This paper proposes an accelerated proximal stochastic variance reduced gradient (ASVRG) method, in which we design a simple and effective momentum acceleration trick. Unlike most…

cs.LG2018

Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)

Xiao Yan, Xinyan Dai, Jie Liu +2

Recently, locality sensitive hashing (LSH) was shown to be effective for MIPS and several algorithms including -ALSH, Sign-ALSH and Simple-LSH have been proposed. In this pape…

cs.LG2018

Norm-Ranging LSH for Maximum Inner Product Search

Xiao Yan, Jinfeng Li, Xinyan Dai +2

Neyshabur and Srebro proposed Simple-LSH, which is the state-of-the-art hashing method for maximum inner product search (MIPS) with performance guarantee. We found that the perform…

cs.LG2018

Bilinear Factor Matrix Norm Minimization for Robust PCA: Algorithms and Applications

Fanhua Shang, James Cheng, Yuanyuan Liu +2

The heavy-tailed distributions of corrupted outliers and singular values of all channels in low-level vision have proven effective priors for many applications such as background m…

cs.LG2018

A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates

Kaiwen Zhou, Fanhua Shang, James Cheng

Recent years have witnessed exciting progress in the study of stochastic variance reduced gradient methods (e.g., SVRG, SAGA), their accelerated variants (e.g, Katyusha) and their…

cs.LG2018

Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization

Fanhua Shang, Yuanyuan Liu, James Cheng

The Schatten quasi-norm was introduced to bridge the gap between the trace norm and rank function. However, existing algorithms are too slow or even impractical for large-scale pro…