English
Related papers

Related papers: Path-Integral Formulation of Unavoidable Canonical…

200 papers

Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take two complex single-forward-pass uncertainty approaches, DUQ…

Machine Learning · Computer Science 2022-01-31 Jishnu Mukhoti , Andreas Kirsch , Joost van Amersfoort , Philip H. S. Torr , Yarin Gal

This paper presents a new canonical duality methodology for solving general nonlinear dynamical systems. Instead of the conventional iterative methods, the discretized nonlinear system is first formulated as a global optimization problem…

Optimization and Control · Mathematics 2016-08-24 Vittorio Latorre , David Yang Gao

Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challenging inverse and ill-posed problems not solvable with…

Machine Learning · Computer Science 2023-02-08 Apostolos F Psaros , Xuhui Meng , Zongren Zou , Ling Guo , George Em Karniadakis

We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learning framework with variational inference. We focus on two…

Machine Learning · Computer Science 2019-11-15 Hongjoon Ahn , Sungmin Cha , Donggyu Lee , Taesup Moon

Industrial dynamical systems often exhibit multi-scale response due to material heterogeneities, operation conditions and complex environmental loadings. In such problems, it is the case that the smallest length-scale of the systems…

Computational Physics · Physics 2020-08-18 Waad Subber , Sayan Ghosh , Piyush Pandita , Yiming Zhang , Liping Wang

Graph Convolutional Network (GCN) has exhibited strong empirical performance in many real-world applications. The vast majority of existing works on GCN primarily focus on the accuracy while ignoring how confident or uncertain a GCN is with…

Machine Learning · Computer Science 2022-10-13 Jian Kang , Qinghai Zhou , Hanghang Tong

Non-Gaussian states are essential for achieving a quantum advantage in continuous-variable (CV) information processing. Among these, coherent superpositions of squeezed states are a foundational resource. While exact higher-order statistics…

Quantum Physics · Physics 2025-11-14 Arash Azizi

Many problems in navigation and tracking require increasingly accurate characterizations of the evolution of uncertainty in nonlinear systems. Nonlinear uncertainty propagation approaches based on Gaussian mixture density approximations…

Machine Learning · Statistics 2025-12-30 Jackson Kulik , Keith A. LeGrand

Uncertainty quantification (UQ) in mathematical models is essential for accurately predicting system behavior under variability. This study provides guidance on method selection for reliable UQ across varied functional behaviors in…

Numerical Analysis · Mathematics 2025-01-17 Alina Chertock , Arsen S. Iskhakov , Anna Iskhakova , Alexander Kurganov

We present a comparison of methods for uncertainty quantification (UQ) in deep learning algorithms in the context of a simple physical system. Three of the most common uncertainty quantification methods - Bayesian Neural Networks (BNN),…

Machine Learning · Computer Science 2020-12-08 João Caldeira , Brian Nord

Neural processes amortize Gaussian process inference, replacing the exact $O(n^3)$ posterior with a learned $O(n)$ map from context sets to predictive distributions. For a class of latent neural processes, we bound the Kullback--Leibler…

Machine Learning · Computer Science 2026-05-22 Robin Young

We decompose the Kullback--Leibler generalization error (GE) -- the expected KL divergence from the data distribution to the trained model -- of unsupervised learning into three non-negative components: model error, data bias, and variance.…

Machine Learning · Statistics 2026-04-15 Gilhan Kim

Uncertainty quantification based on generalized polynomial chaos has been used in many applications. It has also achieved great success in variation-aware design automation. However, almost all existing techniques assume that the parameters…

Numerical Analysis · Mathematics 2019-06-21 Chunfeng Cui , Zheng Zhang

An uncertainty quantification framework is developed for Eulerian-Lagrangian models of particle-laden flows, where the fluid is modeled through a system of partial differential equations in the Eulerian frame and inertial particles are…

Computational Physics · Physics 2018-11-01 Vasileios Fountoulakis , H. S. Udaykumar , Gustaaf B. Jacobs

In this paper, we study the Crank-Nicolson method for temporal dimension and the piecewise quadratic polynomial collocation method for spatial dimensions of time-dependent nonlocal problems. The new theoretical results of such…

Numerical Analysis · Mathematics 2020-06-30 Rongjun Cao , Minghua Chen , Michael K. Ng , Yu-Jiang Wu

Scientific Machine Learning is a new class of approaches that integrate physical knowledge and mechanistic models with data-driven techniques for uncovering governing equations of complex processes. Among the available approaches, Universal…

Machine Learning · Statistics 2024-06-14 Nina Schmid , David Fernandes del Pozo , Willem Waegeman , Jan Hasenauer

Physics-informed neural networks (PINNs) have recently emerged as an alternative way of solving partial differential equations (PDEs) without the need of building elaborate grids, instead, using a straightforward implementation. In…

Analysis of PDEs · Mathematics 2019-09-04 Dongkun Zhang , Lu Lu , Ling Guo , George Em Karniadakis

Information on natural phenomena and engineering systems is typically contained in data. Data can be corrupted by systematic errors in models and experiments. In this paper, we propose a tool to uncover the spatiotemporal solution of the…

Fluid Dynamics · Physics 2023-06-21 Daniel Kelshaw , Luca Magri

In the field of classical discrete systems, specifically substitutional alloys, this study introduces a stochastic thermodynamic approach to address nonlinearity within a canonical ensemble. This approach establishes a nonlinear…

Statistical Mechanics · Physics 2025-12-15 Koretaka Yuge

Quantum field theory in curved spacetime may be defined either through a manifestly unitary canonical approach or via the manifestly covariant path integral formalism. For gauge theories, these two approaches have produced conflicting…

High Energy Physics - Theory · Physics 2013-12-17 William Donnelly , Aron C. Wall