Statistical inference of finite-rank tensors

04/12/2021
by   Hong-Bin Chen, et al.
0

We consider a general statistical inference model of finite-rank tensor products. For any interaction structure and any order of tensor products, we identify the limit free energy of the model in terms of a variational formula. Our approach consists of showing first that the limit free energy must be the viscosity solution to a certain Hamilton-Jacobi equation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/28/2021

Limiting free energy of multi-layer generalized linear models

We compute the high-dimensional limit of the free energy associated with...
research
12/29/2020

Inference for Low-rank Tensors – No Need to Debias

In this paper, we consider the statistical inference for several low-ran...
research
09/24/2019

Tensor Norm, Cubic Power and Gelfand Limit

We establish two inequalities for the nuclear norm and the spectral norm...
research
04/09/2019

Mutual Information for Low-Rank Even-Order Symmetric Tensor Factorization

We consider a statistical model for finite-rank symmetric tensor factori...
research
09/24/2019

Norm of Tensor Product, Tensor Norm, Cubic Power and Gelfand Limit

We establish two inequalities for the nuclear norm and the spectral norm...
research
01/25/2022

Rank-adaptive time integration of tree tensor networks

A rank-adaptive integrator for the approximate solution of high-order te...
research
12/19/2020

Fiducial inference then and now

We conduct a review of the fiducial approach to statistical inference, f...

Please sign up or login with your details

Forgot password? Click here to reset