paper-with-me

홈 › Papers

Parameterized Representations via Implicit Stochastic Modulation for High-Dimensional and High-Order Neural PDE Solvers

2026-06-20 · Zhangyong Liang, Huanhuan Gao arxiv

Solving high-dimensional and high-order PDEs is challenged by the coupled growth of spatial dimensionality and derivative order. Recent stochastic derivative estimators reduce this cost by replacing full derivative tensors with randomized dimension or Taylor estimators, but they are mostly designed for fixed physical parameters and require retraining for each new parameter. We show that direct conditional parameterization of such solvers entangles physical parameters with the high-order automatic differentiation graph, causing extra memory growth and parameter-induced variance amplification. We propose Parameterized Representations via Implicit Stochastic Modulation (PRISM), a plug-and-play framework for parameterized high-dimensional and high-order stochastic neural PDE solvers. PRISM uses a hyper-generator to map physical parameters to affine modulators that scale and shift a purely spatial latent manifold, while keeping parameter branches value-connected but spatial-tangent-disconnected. This design preserves unbiased stochastic dimension and Taylor estimators, removes the parameter encoder from high-order spatial AD, and provides a variance-aware Lipschitz envelope over the parameter space. We prove parameterized unbiasedness, estimation-error bounds, and convergence under bounded stochastic variance. Experiments with PRISM-STDE and PRISM-SDGD on nonlinear parameterized PDEs show stable zero-shot generalization, reduced memory usage, and scalability up to 100,000 dimensions on a single GPU, with efficient low-rank SVD adaptation for unseen parameters.

📄 PDF Abstract BibTeX arXiv:2606.22150

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot Generalization

Similar Papers 제목 키워드 기반

DeepCurrents: Learning Implicit Representations of Shapes with Boundaries

2021-11-17 · CVPR 2022 1 · David Palmer, Dmitriy Smirnov, Stephanie Wang, Albert Chern 외

Recent techniques have been successful in reconstructing surfaces as level sets of learned functions (such as signed distance fields) parameterized by deep neural networks. Many of these methods, however, learn only clos…

Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network

2023-09-21 · NeurIPS 2023 11

Studying the implicit bias of gradient descent (GD) and stochastic gradient descent (SGD) is critical to unveil the underlying mechanism of deep learning. Unfortunately, even for standard linear networks in regression se…

The Geometric Occam's Razor Implicit in Deep Learning

2021-11-30 · Benoit Dherin, Michael Munn, David G. T. Barrett

In over-parameterized deep neural networks there can be many possible parameter configurations that fit the training data exactly. However, the properties of these interpolating solutions are poorly understood. We argue …

ARCDeep Learning

Implicit Regularization in Over-parameterized Neural Networks

2019-03-05 · Masayoshi Kubo, Ryotaro Banno, Hidetaka Manabe, Masataka Minoji

Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in de…

Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization

2018-06-04 · ICLR 2019 5 · Navid Azizan, Babak Hassibi

Stochastic descent methods (of the gradient and mirror varieties) have become increasingly popular in optimization. In fact, it is now widely recognized that the success of deep learning is not only due to the special de…