Establishes statistical and computational optimality thresholds for common subspace estimation and inference under varying SNR regimes, including an impossibility result for adaptive confidence intervals below strong inference SNR.
Tony Cai and Anru Zhang
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Introduces the AR(1)-MSBM for evolving multilayer networks and provides online estimators with minimax-optimal rates and community recovery guarantees under stationarity and non-stationarity via adaptive windowing.
A new matrix zonotope perturbation method with coefficient-space approximation enables faster and less conservative data-driven reachability analysis than prior CMZ or MZ approaches.
Proves approximate Gaussianity of debiased linear forms of eigenvectors in matrix denoising and spiked PCA models under Gaussian noise, then constructs bias/variance estimators yielding minimax-optimal confidence intervals without sample splitting.
Develops a toolbox for two-to-infinity norm bounds on eigenvector deviations under multiple assumption sets and derives generic conditions for perfect clustering
citing papers explorer
-
Statistically and Computationally Optimal Estimation and Inference of Common Subspaces
Establishes statistical and computational optimality thresholds for common subspace estimation and inference under varying SNR regimes, including an impossibility result for adaptive confidence intervals below strong inference SNR.
-
Online Learning for Autoregressive Multilayer Stochastic Block Models under Stationarity and Non-Stationarity
Introduces the AR(1)-MSBM for evolving multilayer networks and provides online estimators with minimax-optimal rates and community recovery guarantees under stationarity and non-stationarity via adaptive windowing.
-
Data-Driven Reachability Analysis Using Matrix Perturbation Theory
A new matrix zonotope perturbation method with coefficient-space approximation enables faster and less conservative data-driven reachability analysis than prior CMZ or MZ approaches.