Partial recovery for top-k ranking: optimality of MLE and suboptimality of the spectral method
From MaRDI portal
Publication:2148993
DOI10.1214/21-AOS2166MaRDI QIDQ2148993FDOQ2148993
Authors: Pinhan Chen, Chao Gao, Anderson Y. Zhang 
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
Recommendations
- Spectral method and regularized MLE are both optimal for top-\(K\) ranking
- A nearly instance optimal algorithm for top-\(k\) ranking under the multinomial logit model
- Partial kernelization for rank aggregation: theory and experiments
- Ranking recovery from limited pairwise comparisons using low-rank matrix completion
- On Confidence-Constrained Rank Recovery in Topic Models
- scientific article
- Rank‐Based Methods for Shrinkage and Selection
- Antithetic and Monte Carlo kernel estimators for partial rankings
- Ranking and empirical minimization of \(U\)-statistics
- Ranking with Partial Information: A Method and an Application
Cites Work
- Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
- Minimax rates of community detection in stochastic block models
- Title not available (Why is that?)
- Entrywise eigenvector analysis of random matrices with low expected rank
- Title not available (Why is that?)
- An introduction to matrix concentration inequalities
- Simple, Robust and Optimal Ranking from Pairwise Comparisons
- Rank Centrality: Ranking from Pairwise Comparisons
- Competitive analysis of the top-\(K\) ranking problem
- Subset Ranking Using Regression
- Variable selection with Hamming loss
- Spectral method and regularized MLE are both optimal for top-\(K\) ranking
- Optimality of spectral clustering in the Gaussian mixture model
- Optimal Variable Selection and Adaptive Noisy Compressed Sensing
Cited In (7)
- Title not available (Why is that?)
- Partial Recovery for Top-$k$ Ranking: Optimality of MLE and Sub-Optimality of Spectral Method
- A General Pairwise Comparison Model for Extremely Sparse Networks
- Variable selection, monotone likelihood ratio and group sparsity
- Optimal full ranking from pairwise comparisons
- On Confidence-Constrained Rank Recovery in Topic Models
- Inference for heteroskedastic PCA with missing data
This page was built for publication: Partial recovery for top-\(k\) ranking: optimality of MLE and suboptimality of the spectral method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2148993)
