PRISM enables zero-shot parameterized high-dimensional high-order neural PDE solvers via implicit stochastic modulation that decouples parameters from the differentiation graph while preserving unbiased estimators.
Title resolution pending
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 frozen-feature neural network with a Gaussian envelope and stochastic dimension sampling produces accurate 1D–3D GPE solutions, but the 1000-dimensional claim rests on a manufactured stationary equation, not GPE dynamics.
citing papers explorer
-
Parameterized Representations via Implicit Stochastic Modulation for High-Dimensional and High-Order Neural PDE Solvers
PRISM enables zero-shot parameterized high-dimensional high-order neural PDE solvers via implicit stochastic modulation that decouples parameters from the differentiation graph while preserving unbiased estimators.
-
Stochastic-Dimension Frozen Sampled Neural Network for High-Dimensional Gross-Pitaevskii Equations on Unbounded Domains
A frozen-feature neural network with a Gaussian envelope and stochastic dimension sampling produces accurate 1D–3D GPE solutions, but the 1000-dimensional claim rests on a manufactured stationary equation, not GPE dynamics.