Partial recovery for top-\(k\) ranking: optimality of MLE and suboptimality of the spectral method
From MaRDI portal
Publication:2148993
DOI10.1214/21-AOS2166MaRDI QIDQ2148993
Anderson Y. Zhang, Pinhan Chen, Chao Gao
Publication date: 24 June 2022
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2006.16485
Related Items (3)
Optimal full ranking from pairwise comparisons ⋮ Variable selection, monotone likelihood ratio and group sparsity ⋮ A General Pairwise Comparison Model for Extremely Sparse Networks
Cites Work
- Unnamed Item
- Unnamed Item
- Minimax rates of community detection in stochastic block models
- Variable selection with Hamming loss
- Optimality of spectral clustering in the Gaussian mixture model
- Entrywise eigenvector analysis of random matrices with low expected rank
- Spectral method and regularized MLE are both optimal for top-\(K\) ranking
- Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
- Simple, Robust and Optimal Ranking from Pairwise Comparisons
- Competitive analysis of the top-K ranking problem
- Optimal Variable Selection and Adaptive Noisy Compressed Sensing
- Subset Ranking Using Regression
- An Introduction to Matrix Concentration Inequalities
- Rank Centrality: Ranking from Pairwise Comparisons
This page was built for publication: Partial recovery for top-\(k\) ranking: optimality of MLE and suboptimality of the spectral method
