Related papers: Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs

Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs

URL: http://arxiv.org/abs/2403.10642v2
Date: Wed, 12 Jun 2024 05:27:43 GMT
Title: Using Uncertainty Quantification to Characterize and Improve Out-of-Domain Learning for PDEs
Authors: S. Chandra Mouli, Danielle C. Maddix, Shima Alizadeh, Gaurav Gupta, Andrew Stuart, Michael W. Mahoney, Yuyang Wang,
Abstract summary: Neural Operators (NOs) have emerged as particularly promising quantification. We show that ensembling several NOs can identify high-error regions and provide good uncertainty estimates. We then introduce Operator-ProbConserv, a method that uses these well-calibrated UQ estimates within the ProbConserv framework to update the model.
Score: 44.890946409769924
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Existing work in scientific machine learning (SciML) has shown that data-driven learning of solution operators can provide a fast approximate alternative to classical numerical partial differential equation (PDE) solvers. Of these, Neural Operators (NOs) have emerged as particularly promising. We observe that several uncertainty quantification (UQ) methods for NOs fail for test inputs that are even moderately out-of-domain (OOD), even when the model approximates the solution well for in-domain tasks. To address this limitation, we show that ensembling several NOs can identify high-error regions and provide good uncertainty estimates that are well-correlated with prediction errors. Based on this, we propose a cost-effective alternative, DiverseNO, that mimics the properties of the ensemble by encouraging diverse predictions from its multiple heads in the last feed-forward layer. We then introduce Operator-ProbConserv, a method that uses these well-calibrated UQ estimates within the ProbConserv framework to update the model. Our empirical results show that Operator-ProbConserv enhances OOD model performance for a variety of challenging PDE problems and satisfies physical constraints such as conservation laws.

Related papers

Learning Solutions of Stochastic Optimization Problems with Bayesian Neural Networks [4.202961704179733]
In many real-world settings, some of these parameters are unknown or uncertain. Recent research focuses on predicting the value of unknown parameters using available contextual features. We propose a novel framework that models uncertainty Neural Networks (BNNs) and propagates this uncertainty into the mathematical solver.
arXiv Detail & Related papers (2024-06-05T09:11:46Z)
Neural Operator induced Gaussian Process framework for probabilistic solution of parametric partial differential equations [8.528817025440746]
We propose a novel Neural Operator-induced Gaussian Process (NOGaP) for partial differential equations. The proposed framework leads to improved prediction accuracy and offers a quantifiable measure of uncertainty. The results demonstrate superior accuracy and expected uncertainty characteristics, suggesting the promising potential of NOGaP.
arXiv Detail & Related papers (2024-04-24T03:16:48Z)
Model-Free Local Recalibration of Neural Networks [0.0]
Uncalibrated probabilistic forecasts are of limited use for many important decision-making tasks. We propose a localized recalibration of ANN predictive distributions using the dimension-reduced representation of the input. We show that our method has good performance compared to alternative approaches.
arXiv Detail & Related papers (2024-03-09T01:58:45Z)
Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution [110.99891169486366]
We propose a method that integrates efficient and precise uncertainty quantification into a deep learning-based surrogate model. Our method endows deep learning-based surrogate models with robust and efficient uncertainty quantification capabilities for both forward and inverse problems. Our method excels at propagating uncertainty over extended auto-regressive rollouts, making it suitable for scenarios involving long-term predictions.
arXiv Detail & Related papers (2024-02-13T11:22:59Z)
Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
arXiv Detail & Related papers (2023-12-07T15:55:58Z)
Evaluating Uncertainty Quantification approaches for Neural PDEs in scientific applications [0.0]
This work evaluates various Uncertainty Quantification (UQ) approaches for both Forward and Inverse Problems in scientific applications. Specifically, we investigate the effectiveness of Bayesian methods, such as Hamiltonian Monte Carlo (HMC) and Monte-Carlo Dropout (MCD) Our results indicate that Neural PDEs can effectively reconstruct flow systems and predict the associated unknown parameters.
arXiv Detail & Related papers (2023-11-08T04:52:20Z)
Human Trajectory Forecasting with Explainable Behavioral Uncertainty [63.62824628085961]
Human trajectory forecasting helps to understand and predict human behaviors, enabling applications from social robots to self-driving cars. Model-free methods offer superior prediction accuracy but lack explainability, while model-based methods provide explainability but cannot predict well. We show that BNSP-SFM achieves up to a 50% improvement in prediction accuracy, compared with 11 state-of-the-art methods.
arXiv Detail & Related papers (2023-07-04T16:45:21Z)
Accurate and Reliable Forecasting using Stochastic Differential Equations [48.21369419647511]
It is critical yet challenging for deep learning models to properly characterize uncertainty that is pervasive in real-world environments. This paper develops SDE-HNN to characterize the interaction between the predictive mean and variance of HNNs for accurate and reliable regression. Experiments on the challenging datasets show that our method significantly outperforms the state-of-the-art baselines in terms of both predictive performance and uncertainty quantification.
arXiv Detail & Related papers (2021-03-28T04:18:11Z)
Attribute-Guided Adversarial Training for Robustness to Natural Perturbations [64.35805267250682]
We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations.
arXiv Detail & Related papers (2020-12-03T10:17:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.