Statistical Methods for Minimax Estimation in Linear Models with Unknown Design Over Finite Alphabets
DOI10.1137/21M1398860zbMath1493.62112arXiv1711.04145MaRDI QIDQ5073629
Publication date: 3 May 2022
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1711.04145
blind source separationdictionary learningexact recoveryminimax theoryLloyd's algorithmcombinatorial linear model
Asymptotic properties of parametric estimators (62F12) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Linear regression; mixed models (62J05) Parametric inference under constraints (62F30)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A clustering approach for the blind separation of multiple finite alphabet sequences from a single linear mixture
- Independent component analysis, a new concept?
- Multiscale blind source separation
- A fast algorithm with minimax optimal guarantees for topic models with an unknown number of topics
- Optimal rates of estimation for multi-reference alignment
- Structured matrix estimation and completion
- Provable ICA with unknown Gaussian noise, and implications for Gaussian mixtures and autoencoders
- Independent component analysis: recent advances
- The Optimal Hard Threshold for Singular Values is <inline-formula> <tex-math notation="TeX">\(4/\sqrt {3}\) </tex-math></inline-formula>
- Fast Nonnegative Matrix Factorization: An Active-Set-Like Method and Comparisons
- ICA in Boolean XOR Mixtures
- Channel identification for high speed digital communications
- Binary Independent Component Analysis With or Mixtures
- Identifiability for Blind Source Separation of Multiple Finite Alphabet Linear Mixtures
- Linear Independent Component Analysis Over Finite Fields: Algorithms and Bounds
- Bayesian Non-Parametric Hidden Markov Models with Applications in Genomics
- Learning the parts of objects by non-negative matrix factorization
- Computing a nonnegative matrix factorization -- provably
- Blind separation and equalization using fractional sampling of digital communications signals
This page was built for publication: Statistical Methods for Minimax Estimation in Linear Models with Unknown Design Over Finite Alphabets
