2 code implementations • 14 Dec 2021 • Thomas O'Leary-Roseberry, Xiaosong Du, Anirban Chaudhuri, Joaquim R. R. A. Martins, Karen Willcox, Omar Ghattas
We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs.
2 code implementations • 29 Jan 2021 • Elizabeth Qian, Ionut-Gabriel Farcas, Karen Willcox
First, ideas from projection-based model reduction are used to explicitly parametrize the learned model by low-dimensional polynomial operators which reflect the known form of the governing PDE.
no code implementations • 13 Jan 2021 • Anirban Chaudhuri, Boris Kramer, Matthew Norton, Johannes O. Royset, Karen Willcox
CRiBDO is contrasted with reliability-based design optimization (RBDO), where uncertainties are accounted for via the probability of failure, through a structural and a thermal design problem.
Optimization and Control Computational Engineering, Finance, and Science Data Analysis, Statistics and Probability Computation
1 code implementation • 6 Aug 2020 • Shane A. McQuarrie, Cheng Huang, Karen Willcox
With appropriate regularization and an informed selection of learning variables, the reduced-order models exhibit high accuracy in re-predicting the training regime and acceptable accuracy in predicting future dynamics, while achieving close to a million times speedup in computational cost.
Computational Engineering, Finance, and Science J.2
1 code implementation • 22 Feb 2020 • Peter Benner, Pawan Goyal, Boris Kramer, Benjamin Peherstorfer, Karen Willcox
The proposed method learns operators for the linear and polynomially nonlinear dynamics via a least-squares problem, where the given non-polynomial terms are incorporated in the right-hand side.
4 code implementations • 17 Dec 2019 • Elizabeth Qian, Boris Kramer, Benjamin Peherstorfer, Karen Willcox
The lifting map is applied to data obtained by evaluating a model for the original nonlinear system.
BIG-bench Machine Learning Physics-informed machine learning
2 code implementations • 9 Aug 2019 • Renee Swischuk, Boris Kramer, Cheng Huang, Karen Willcox
The machine learning perspective brings the flexibility to use transformed physical variables to define the POD basis.
no code implementations • NeurIPS 2018 • Alexandre Marques, Remi Lam, Karen Willcox
We introduce an algorithm to locate contours of functions that are expensive to evaluate.
no code implementations • NeurIPS 2017 • Remi Lam, Karen Willcox
We consider the task of optimizing an objective function subject to inequality constraints when both the objective and the constraints are expensive to evaluate.
no code implementations • NeurIPS 2016 • Remi Lam, Karen Willcox, David H. Wolpert
We consider the problem of optimizing an expensive objective function when a finite budget of total evaluations is prescribed.