Y
Yudong Chen
Researcher at Cornell University
Publications - 135
Citations - 8756
Yudong Chen is an academic researcher from Cornell University. The author has contributed to research in topics: Matrix completion & Convex optimization. The author has an hindex of 33, co-authored 117 publications receiving 6873 citations. Previous affiliations of Yudong Chen include Tsinghua University & National University of Singapore.
Papers
More filters
Journal ArticleDOI
User Association for Load Balancing in Heterogeneous Cellular Networks
Ye Qiaoyang,Beiyu Rong,Yudong Chen,Mazin Al-Shalash,Constantine Caramanis,Jeffrey G. Andrews +5 more
TL;DR: In this paper, the authors provide a low-complexity distributed algorithm that converges to a near-optimal solution with a theoretical performance guarantee, and observe that simple per-tier biasing loses surprisingly little, if the bias values Aj are chosen carefully.
Posted Content
User Association for Load Balancing in Heterogeneous Cellular Networks
Ye Qiaoyang,Beiyu Rong,Yudong Chen,Mazin Al-Shalash,Constantine Caramanis,Jeffrey G. Andrews +5 more
TL;DR: A low-complexity distributed algorithm that converges to a near-optimal solution with a theoretical performance guarantee is provided, and it is observed that simple per-tier biasing loses surprisingly little, if the bias values Aj are chosen carefully.
Journal ArticleDOI
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm
TL;DR: Zhang et al. as mentioned in this paper proposed a tensor robust principal component analysis (TRPCA) model based on the tensor-tensor product (or t-product) to recover the low-rank and sparse components from their sum.
Proceedings Article
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
TL;DR: A main result of this work is a sharp analysis of two robust distributed gradient descent algorithms based on median and trimmed mean operations, respectively, which are shown to achieve order-optimal statistical error rates for strongly convex losses.
Proceedings ArticleDOI
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
TL;DR: This work proves that under certain suitable assumptions, it can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the l1-norm.