A LoRA-style low-rank factorization of the hypernetwork output weight matrix reduces parameters in physics-informed HyperDeepONets and achieves equal or better accuracy on five ODE/PDE benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Low-rank adaptive physics-informed HyperDeepONets for solving differential equations
A LoRA-style low-rank factorization of the hypernetwork output weight matrix reduces parameters in physics-informed HyperDeepONets and achieves equal or better accuracy on five ODE/PDE benchmarks.