Deep Latent Regularity Network for Modeling Stochastic Partial Differential Equations

Authors: Shiqi Gong, Peiyan Hu, Qi Meng, Yue Wang, Rongchan Zhu, Bingguang Chen, Zhiming Ma, Hao Ni, Tie-Yan Liu

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments on various SPDEs including the dynamic Φ4 1 model and the stochastic 2D Navier-Stokes equation to predict their solutions, and the results demonstrate that the proposed DLR-Net can achieve SOTA accuracy compared with the baselines.
Researcher Affiliation Collaboration 1 Academy of Mathematics and Systems Science, Chinese Academy of Sciences 2 Microsoft Research AI4Science 3 Bielefeld University 4 Department of Mathematics, University College London 5 The Alan Turing Institute
Pseudocode Yes Algorithm 1: Generation of Model Feature Vectors
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the methodology described.
Open Datasets Yes Space-time white noise ξ and reference solution u on this grid are given by numerical simulator in (Chevyrev, Gerasimovics, and Weber 2021) on this grid.
Dataset Splits No The paper mentions 'training data size N = 1000 or 10000' and training and testing models, but does not provide specific train/validation/test split percentages or sample counts for each split.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers, such as library or solver names.
Experiment Setup Yes For this equation, we use two RF blocks with height n = 2 and α = (3, 1) in the feature sets. In the decoder layer, we use 4-layer 2d-FNO with s1 = 16, s2 = 16 and width = 8.