Sobolev regularization on the witness function enables global convergence of MMD gradient flows for both sampling and generative modeling without isoperimetric assumptions.
On the limited memory
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
A hybrid least squares / gradient descent method accelerates MIONet training by exploiting multilinear structure in last-layer branch parameters via alternating least squares with Kronecker/Khatri-Rao factorization.
citing papers explorer
-
Sobolev Regularized MMD Gradient Flow
Sobolev regularization on the witness function enables global convergence of MMD gradient flows for both sampling and generative modeling without isoperimetric assumptions.
-
Hybrid Least Squares/Gradient Descent Methods for MIONets
A hybrid least squares / gradient descent method accelerates MIONet training by exploiting multilinear structure in last-layer branch parameters via alternating least squares with Kronecker/Khatri-Rao factorization.