BibTeX

@article{2409.18402v1,
Author        = {Ruoxi Jiang and Peter Y. Lu and Rebecca Willett},
Title         = {Embed and Emulate: Contrastive representations for simulation-based
  inference},
Eprint        = {2409.18402v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.LG},
Abstract      = {Scientific modeling and engineering applications rely heavily on parameter
estimation methods to fit physical models and calibrate numerical simulations
using real-world measurements. In the absence of analytic statistical models
with tractable likelihoods, modern simulation-based inference (SBI) methods
first use a numerical simulator to generate a dataset of parameters and
simulated outputs. This dataset is then used to approximate the likelihood and
estimate the system parameters given observation data. Several SBI methods
employ machine learning emulators to accelerate data generation and parameter
estimation. However, applying these approaches to high-dimensional physical
systems remains challenging due to the cost and complexity of training
high-dimensional emulators. This paper introduces Embed and Emulate (E&E): a
new SBI method based on contrastive learning that efficiently handles
high-dimensional data and complex, multimodal parameter posteriors. E&E learns
a low-dimensional latent embedding of the data (i.e., a summary statistic) and
a corresponding fast emulator in the latent space, eliminating the need to run
expensive simulations or a high dimensional emulator during inference. We
illustrate the theoretical properties of the learned latent space through a
synthetic experiment and demonstrate superior performance over existing methods
in a realistic, non-identifiable parameter estimation task using the
high-dimensional, chaotic Lorenz 96 system.},
Year          = {2024},
Month         = {Sep},
Url           = {http://arxiv.org/abs/2409.18402v1},
File          = {2409.18402v1.pdf}
}