activity
20192022
most citedLimiting free energy of multi-layer generalized linear models

2 citations · 5 across the 4 of their papers we have counts for

collaborators
Showing math.PRShow all

8 papers · 1 filter

math.PR20221 cited

Rare transitions in noisy heteroclinic networks

Yuri Bakhtin, Hong-Bin Chen, Zsolt Pajor-Gyulai

We study small white noise perturbations of planar dynamical systems with heteroclinic networks in the limit of vanishing noise. We show that the probabilities of transitions betwe…

math.PR20212 cited

Limiting free energy of multi-layer generalized linear models

Hong-Bin Chen, Jiaming Xia

We compute the high-dimensional limit of the free energy associated with a multi-layer generalized linear model. Under certain technical assumptions, we identify the limit in terms…

math.PR20211 cited

Dimension-free log-Sobolev inequalities for mixture distributions

Hong-Bin Chen, Sinho Chewi, Jonathan Niles-Weed

We prove that if is a family of probability measures which satisfy the log-Sobolev inequality and whose pairwise chi-squared divergences are uniformly b…

math.PR2020

Hamilton-Jacobi equations for inference of matrix tensor products

Hong-Bin Chen, Jiaming Xia

We study the high-dimensional limit of the free energy associated with the inference problem of finite-rank matrix tensor products. In general, we bound the limit from above by the…

math.PR20201 cited

Hamilton-Jacobi equations for nonsymmetric matrix inference

Hong-Bin Chen

We study the high-dimensional limit of the free energy associated with the inference problem of a rank-one nonsymmetric matrix. The matrix is expressed as the outer product of two…

math.PR2020

Asymptotics of smoothed Wasserstein distances

Hong-Bin Chen, Jonathan Niles-Weed

We investigate contraction of the Wasserstein distances on under Gaussian smoothing. It is well known that the heat semigroup is exponentially contractive with respe…