The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
The singular value matrix decomposition plays a ubiquitous role throughout statistics and
related fields. Myriad applications including clustering, classification, and dimensionality …
related fields. Myriad applications including clustering, classification, and dimensionality …
Recent progress in combinatorial random matrix theory
VH Vu - 2021 - projecteuclid.org
Recent progress in combinatorial random matrix theory Page 1 Probability Surveys Vol. 18 (2021)
179–200 ISSN: 1549-5787 https://doi.org/10.1214/20-PS346 Recent progress in combinatorial …
179–200 ISSN: 1549-5787 https://doi.org/10.1214/20-PS346 Recent progress in combinatorial …
Laplacian canonization: A minimalist approach to sign and basis invariant spectral embedding
Spectral embedding is a powerful graph embedding technique that has received a lot of
attention recently due to its effectiveness on Graph Transformers. However, from a …
attention recently due to its effectiveness on Graph Transformers. However, from a …
Introduction to graph signal processing
Graph signal processing deals with signals whose domain, defined by a graph, is irregular.
An overview of basic graph forms and definitions is presented first. Spectral analysis of …
An overview of basic graph forms and definitions is presented first. Spectral analysis of …
Sum-of-squares lower bounds for sherrington-kirkpatrick via planted affine planes
The Sum-of-Squares (SoS) hierarchy is a semi-definite programming meta-algorithm that
captures state-of-the-art polynomial time guarantees for many optimization problems such …
captures state-of-the-art polynomial time guarantees for many optimization problems such …
Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods
S Ling - Applied and Computational Harmonic Analysis, 2022 - Elsevier
Group synchronization asks to recover group elements from their pairwise measurements. It
has found numerous applications across various scientific disciplines. In this work, we focus …
has found numerous applications across various scientific disciplines. In this work, we focus …
Learning with hyperspherical uniformity
Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear
function approximation. In order to achieve good generalization on unseen data, a suitable …
function approximation. In order to achieve good generalization on unseen data, a suitable …
Data analytics on graphs Part I: Graphs and spectra on graphs
Abstract The area of Data Analytics on graphs promises a paradigm shift, as we approach
information processing of new classes of data which are typically acquired on irregular but …
information processing of new classes of data which are typically acquired on irregular but …
Matrix denoising: Bayes-optimal estimators via low-degree polynomials
G Semerjian - Journal of Statistical Physics, 2024 - Springer
We consider the additive version of the matrix denoising problem, where a random
symmetric matrix S of size n has to be inferred from the observation of Y= S+ Z, with Z an …
symmetric matrix S of size n has to be inferred from the observation of Y= S+ Z, with Z an …
Spiked separable covariance matrices and principal components
Spiked separable covariance matrices and principal components Page 1 The Annals of Statistics
2021, Vol. 49, No. 2, 1113–1138 https://doi.org/10.1214/20-AOS1995 © Institute of Mathematical …
2021, Vol. 49, No. 2, 1113–1138 https://doi.org/10.1214/20-AOS1995 © Institute of Mathematical …