Uncertainty quantification for deeponets with ensemble kalman inversion

arXiv:2403.03444v1 Announce Type: new
Abstract: In recent years, operator learning, particularly the DeepONet, has received much attention for efficiently learning complex mappings between input and output functions across diverse fields. However, in practical scenarios with limited and noisy data, accessing the uncertainty in DeepONet predictions becomes essential, especially in mission-critical or safety-critical applications. Existing methods, either computationally intensive or yielding unsatisfactory uncertainty quantification, leave room for developing efficient and informative uncertainty quantification (UQ) techniques tailored for DeepONets. In this work, …

abstract arxiv attention cs.ai cs.lg cs.na data deeponet diverse ensemble fields functions however math.na mission practical predictions quantification safety safety-critical stat.ml type uncertainty