تقرير
Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models
العنوان: | Improving the performance of Stein variational inference through extreme sparsification of physically-constrained neural network models |
---|---|
المؤلفون: | Padmanabha, Govinda Anantha, Fuhg, Jan Niklas, Safta, Cosmin, Jones, Reese E., Bouklas, Nikolaos |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Computational Engineering, Finance, and Science |
الوصف: | Most scientific machine learning (SciML) applications of neural networks involve hundreds to thousands of parameters, and hence, uncertainty quantification for such models is plagued by the curse of dimensionality. Using physical applications, we show that $L_0$ sparsification prior to Stein variational gradient descent ($L_0$+SVGD) is a more robust and efficient means of uncertainty quantification, in terms of computational cost and performance than the direct application of SGVD or projected SGVD methods. Specifically, $L_0$+SVGD demonstrates superior resilience to noise, the ability to perform well in extrapolated regions, and a faster convergence rate to an optimal solution. Comment: 30 pages, 11 figures |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2407.00761 |
رقم الأكسشن: | edsarx.2407.00761 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |