A two-stage algorithm learns a coordinate chart and a low-rank tensor source for a linear PDE, reducing supervised learning on manifolds to independent 1D integrals with automatic intrinsic dimension discovery.
Proceedings of the Fourth Eurographics Symposium on Geometry Processing , volume=
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
-
Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE
A two-stage algorithm learns a coordinate chart and a low-rank tensor source for a linear PDE, reducing supervised learning on manifolds to independent 1D integrals with automatic intrinsic dimension discovery.