Cauchy noise loss for stochastic optimization of random matrix models via free deterministic equivalents
arXiv:1804.03154
Abstract
For random matrix models, the parameter estimation based on the traditional likelihood functions is not straightforward in particular when we have only one sample matrix. We introduce a new parameter optimization method for random matrix models which works even in such a case. The method is based on the spectral distribution instead of the traditional likelihood. In the method, the Cauchy noise has an essential role because the free deterministic equivalent, which is a tool in free probability theory, allows us to approximate the spectral distribution perturbed by Cauchy noises by a smooth and accessible density function. Moreover, we study an asymptotic property of determination gap, which has a similar role as generalization gap. Besides, we propose a new dimensionality recovery method for the signal-plus-noise model, and experimentally demonstrate that it recovers the rank of the signal part even if the true rank is not small. It is a simultaneous rank selection and parameter estimation procedure.
arXiv comment29 pages, 13 figures, v3: minor correction. Submitted. Our simulation code is available at https://github.com/ThayaFluss/cnl. Submitted to a journal
References in corpus (5)
- New insights and perspectives on the natural gradient method
- Improved subspace estimation for multivariate observations of high dimension: the deterministic signals case
- Second Order Freeness and Fluctuations of Random Matrices, III. Higher order freeness and free cumulants
- Rigorous mean field model for CPA: Anderson model with free random variables
- Free deterministic equivalent Z-scores of compound Wishart models: A goodness of fit test of 2DARMA models