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.
A hybrid iterative method based on
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
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.