arXiv:2104.05360 [math.PR]AbstractReferencesReviewsResources
Statistical inference of finite-rank tensors
Hong-Bin Chen, Jean-Christophe Mourrat, Jiaming Xia
Published 2021-04-12Version 1
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.
Comments: 21 pages
Related articles: Most relevant | Search more
arXiv:1904.05294 [math.PR] (Published 2019-04-10)
Hamilton-Jacobi equations for finite-rank matrix inference
arXiv:2308.10715 [math.PR] (Published 2023-08-21)
Un-inverting the Parisi formula
arXiv:2108.12615 [math.PR] (Published 2021-08-28)
Limiting free energy of multi-layer generalized linear models