Uncertainty Quantification with Bayesian Higher Order ReLU KANs
We introduce the first method of uncertainty quantification in the domain of Kolmogorov-Arnold Networks, specifically focusing on (Higher Order) ReLUKANs to enhance computational efficiency given the computational demands of Bayesian methods. The method we propose is general in nature, providing access to both epistemic and aleatoric uncertainties. It is also capable of generalization to other various basis functions. We validate our method through a series of closure tests, including simple one-dimensional functions and application to the domain of (Stochastic) Partial Differential Equations. Referring to the latter, we demonstrate the method's ability to correctly identify functional dependencies introduced through the inclusion of a stochastic term. The code supporting this work can be found at https://github.com/wmdataphys/Bayesian-HR-KAN
Code (1)
Tasks
Computational EfficiencyKolmogorov-Arnold NetworksUncertainty QuantificationSimilar Papers 제목 키워드 기반
Uncertainty Quantification for Sparse Deep Learning
Deep learning methods continue to have a decided impact on machine learning, both in theory and in practice. Statistical theoretical developments have been mostly concerned with approximability or rates of estimation whe…
Deep LearningUncertainty QuantificationvalidMP-GELU Bayesian Neural Networks: Moment Propagation by GELU Nonlinearity
Bayesian neural networks (BNNs) have been an important framework in the study of uncertainty quantification. Deterministic variational inference, one of the inference methods, utilizes moment propagation to compute the p…
Uncertainty QuantificationVariational InferenceThe Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions
Deep learning models achieve high predictive accuracy in a broad spectrum of tasks, but rigorously quantifying their predictive uncertainty remains challenging. Usable estimates of predictive uncertainty should (1) cover…
Uncertainty QuantificationPartial Trace-Class Bayesian Neural Networks
Bayesian neural networks (BNNs) allow rigorous uncertainty quantification in deep learning, but often come at a prohibitive computational cost. We propose three different innovative architectures of partial trace-class B…
Uncertainty-Aware Sparse Identification of Dynamical Systems via Bayesian Model Averaging
In many problems of data-driven modeling for dynamical systems, the governing equations are not known a priori and must be selected phenomenologically from a large set of candidate interactions and basis functions. In su…