L
Laming Chen
Researcher at Tsinghua University
Publications - 36
Citations - 574
Laming Chen is an academic researcher from Tsinghua University. The author has contributed to research in topics: Compressed sensing & Matching pursuit. The author has an hindex of 12, co-authored 36 publications receiving 467 citations.
Papers
More filters
Proceedings Article
Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity
TL;DR: In this paper, the authors proposed a novel algorithm to greatly accelerate the greedy MAP inference for determinantal point process (DPP) and adapts to scenarios where the repulsion is only required among nearby few items in the result sequence.
Journal ArticleDOI
The Convergence Guarantees of a Non-Convex Approach for Sparse Recovery
Laming Chen,Yuantao Gu +1 more
TL;DR: In this article, the concept of weak convexity is incorporated into a class of sparsity-inducing penalties to characterize the non-convexity of a non-Convex approach for sparse recovery.
Posted Content
Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity
TL;DR: This paper proposes a novel algorithm to greatly accelerate the greedy MAP inference for DPP, and shows that this algorithm is significantly faster than state-of-the-art competitors, and provides a better relevance-diversity trade-off on several public datasets.
Journal ArticleDOI
Perturbation Analysis of Orthogonal Matching Pursuit
Jie Ding,Laming Chen,Yuantao Gu +2 more
TL;DR: The performance of OMP is analyzed under general perturbations, which means both y and Φ are perturbed and it is proved that the sufficient conditions for support recovery of the best k-term approximation of x can be relaxed, and the support can even be recovered in the order of the entries' magnitude.
Journal ArticleDOI
Square-Root Lasso With Nonconvex Regularization: An ADMM Approach
TL;DR: A class of nonconvex sparsity-inducing penalties to the square-root Lasso is introduced to achieve better sparse recovery performance over the convex counterpart.