Identifiability of parametric random matrix models

12/27/2018
by   Tomohiro Hayase, et al.
0

We investigate parameter identifiability of spectral distributions of random matrices. In particular, we treat compound Wishart type and signal-plus-noise type. We show that each model is identifiable up to some kind of rotation of parameter space. Our method is based on free probability theory.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/09/2018

Cauchy noise loss for stochastic optimization of random matrix models via free deterministic equivalents

Based on free probability theory and stochastic optimization, we introdu...
research
01/28/2022

The limiting spectral distribution of large dimensional general information-plus-noise type matrices

Let X_n be n× N random complex matrices, R_n and T_n be non-random compl...
research
05/11/2021

ORCEA: Object Recognition by Continuous Evidence Assimilation

ORCEA is a novel object recognition method applicable for objects descri...
research
04/28/2021

Detection of Signal in the Spiked Rectangular Models

We consider the problem of detecting signals in the rank-one signal-plus...
research
06/14/2020

The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry

The Fisher information matrix (FIM) is fundamental for understanding the...
research
06/04/2018

Phase-type distributions in population genetics

Probability modelling for DNA sequence evolution is well established and...
research
02/03/2023

Analysis of the limiting spectral distribution of large dimensional General information-plus-noise type matrices

In this paper, we derive the analytical behavior of the limiting spectra...

Please sign up or login with your details

Forgot password? Click here to reset