arXiv:1904.05294 [math.PR]AbstractReferencesReviewsResources
Hamilton-Jacobi equations for finite-rank matrix inference
Published 2019-04-10Version 1
We compute the large-scale limit of the free energy associated with the problem of inference of a finite-rank matrix. The method follows the principle put forward in arXiv:1811.01432 which consists in identifying a suitable Hamilton-Jacobi equation satisfied by the limit free energy. We simplify the approach of arXiv:1811.01432 using a notion of weak solution of the Hamilton-Jacobi equation which is more convenient to work with and is applicable whenever the non-linearity in the equation is convex.
Comments: 26 pages
Categories: math.PR, cond-mat.dis-nn
Related articles: Most relevant | Search more
arXiv:2104.05360 [math.PR] (Published 2021-04-12)
Statistical inference of finite-rank tensors
arXiv:2308.10715 [math.PR] (Published 2023-08-21)
Un-inverting the Parisi formula
arXiv:2311.08980 [math.PR] (Published 2023-11-15)
On the free energy of vector spin glasses with non-convex interactions