This paper proposes a new method to adapt ROMs for new parameter settings.
problem ROMs lack robustness when applied to new parameter settings.
method Regression trees on Grassmann Manifold to learn the mapping between parameters and POD bases.
result The proposed method is capable of establishing the mapping between parameters and POD bases, thus adapting ROMs for new parameters.
This work ensures stability in POD basis interpolation for pMOR in hyperelasticity.
problem Stability of POD basis interpolation on Grassmann manifolds for pMOR in hyperelasticity.
method Stability conditions derived from Grassmannian Exponential map and principal angles.
result Explicit stability conditions for practical pMOR applications and non-monotonic error behavior.
This work proposes a novel method for interpolating ROMs without solving FEM models.
problem Interpolating ROMs for unseen parameter values without solving FEM models.
method Non-intrusive Space-Time POD interpolation on compact Stiefel manifolds.
result Robust ROMs derived for unseen parameter values with strong correlations to high-fidelity simulations.
A new method uses neural networks to improve POD-Galerkin models for complex systems.
problem Improving computational efficiency and accuracy in solving non-linear high-dimensional systems.
method Deep learning-based closure modeling using neural networks to approximate POD-Galerkin operators.
result The CD-ROM approach produces more accurate and stable models for complex systems.
A new method combines POD and PCE for predicting multidimensional physical fields.
problem Predicting multidimensional non-linear fields from limited data.
method Combines Proper Orthogonal Decomposition (POD) and Polynomial Chaos Expansion (PCE).
result Demonstrates improved prediction accuracy and interpretability.
Surrogate models improve tidal model calibration efficiency.
problem Efficiently calibrate complex tidal models for climate change scenarios.
method Proposes two surrogate-based methods to replace complex models: PODEn3DVAR and POD-PCE-3DVAR.
result Both methods show superior convergence and robustness to noise compared to classical 3DVAR.
Reduced-order model improves LES for atmospheric pollutant dispersion.
problem Accurate near-field pollutant concentration tracking in urban areas.
method Combining POD and GPR for non-intrusive reduced-order modeling.
result Component-by-component optimization captures spatial scales in high-order modes.
Paper uses autoencoders for efficient reduced-order modeling of eigenvalue problems.
problem Efficiently modeling eigenvalue problems in high dimensions.
method Autoencoder-based reduced-order modeling for eigenvalue problems.
result Autoencoder-based models outperform standard POD-Galerkin methods in neutron diffusion applications.
Adapts POD basis for parametric ROMs using pGP.
problem Updating POD basis for accurate system behavior over parameter space.
method Formulates problem as supervised statistical learning, uses pGP to learn mapping between parameter space and Grassmann manifold.
result Proposes pGP for optimal estimation of POD basis parameters and quantifies uncertainty.
Paper reduces expensive financial risk simulations through efficient MOR.
problem Expensive simulations of financial risk models.
method Model order reduction (MOR) using proper orthogonal decomposition (POD) with adaptive greedy sampling.
result MOR approach reduces computational cost for financial risk analysis.
Review and compare model order reduction methods for process engineering.
problem Creating computationally efficient yet accurate models for real-time applications.
method Nonlinear model order reduction methods, including general-purpose and tailored approaches for chemical processes.
result Comparison of eight model order reduction methods applied to an air separation process model.
BayPOD-AL learns reduced-order models from high-fidelity data efficiently.
problem Capturing dynamics of complex systems with large training datasets.
method Bayesian active learning based on uncertainty-aware POD.
result BayPOD-AL reduces computational cost and improves model accuracy.
Convolutional networks predict turbulence from wall quantities.
problem Predicting turbulence fields from wall-shear-stress components and wall pressure.
method Two CNN models: FCN and FCN-POD, trained on DNS data.
result FCN and FCN-POD models outperform EPOD in predicting turbulence fields.
Efficient surrogate modeling for complex PDEs with physical laws.
problem High computational cost of repeated PDE simulations.
method LC-prior Gaussian process with POD and RBF-FD.
result Significantly reduced computational cost and improved accuracy.
Enhanced autoencoders improve ROMs for PDEs by capturing essential properties.
problem Autoencoders struggle to capture essential properties for accurate ROMs.
method Introduced symmetric Convolutional AutoEncoders (CAEs) that preserve manifold properties.
result Symmetric CAEs yield more accurate latent trajectories and robust models.
This paper presents a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process. The method combines the perspectives of model reduction and machine learning. Model reduction brin…
Efficiently trains BERT on academic GPUs in 12 days.
problem Training large-scale BERT models is expensive and time-consuming.
method Optimizes training on multiple GPUs and nodes, reducing costs.
result Trains BERT on academic GPUs in 12 days, not requiring expensive hardware.
The objective of this paper is to investigate how noisy and incomplete observations can be integrated in the process of building a reduced-order model. This problematic arises in many scientific domains where there exists a need for accurate low-order descriptions of highly-complex phenomena, which can not be directly …
Deep learning is extremely computationally intensive, and hardware vendors have responded by building faster accelerators in large clusters. Training deep learning models at petaFLOPS scale requires overcoming both algorithmic and systems software challenges. In this paper, we discuss three systems-related optimization…
European options can be priced by solving parabolic partial(-integro) differential equations under stochastic volatility and jump-diffusion models like Heston, Merton, and Bates models. American option prices can be obtained by solving linear complementary problems (LCPs) with the same operators. A finite difference di…
In this paper, we present a new nonintrusive reduced basis method when a cheap low-fidelity model and expensive high-fidelity model are available. The method relies on proper orthogonal decomposition (POD) to generate the high-fidelity reduced basis and a shallow multilayer perceptron to learn the high-fidelity reduced…
Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by operating on a sparse representation of graph adjacency matrices. As we look to scale up these models using custom hardware, a natural assum…
As a robust nonlinear similarity measure in kernel space, correntropy has received increasing attention in domains of machine learning and signal processing. In particular, the maximum correntropy criterion (MCC) has recently been successfully applied in robust regression and filtering. The default kernel function in c…
LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
problem LLM evaluation suffers from systematic biases and lacks reliable positive judgments.
method Formulate LLM evaluation as a positive-unlabelled learning problem and propose a geometric auditing framework based on Partial Optimal Transport.
result Improved alignment with human preferences, increased robustness to presentation biases, and interpretable confidence estimates.
Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.
problem Expensive training of large neural networks limits research contributions.
method Learning@home: decentralized Mixture-of-Experts for large, poorly connected participants.
result Performance and reliability of Learning@home surpass conventional distributed training.
A model order reduction framework reduces financial risk analysis models efficiently.
problem Simulating high-dimensional financial risk models.
method Adaptive greedy sampling based on POD and surrogate modeling.
result Reduced models provide significant speedup with excellent accuracy.
xVAE models extreme turbulence events in turbulent flows.
problem Capturing extreme events in turbulent flows.
method Max-infinitely divisible process with heavy-tailed distributions embedded into a standard VAE framework.
result xVAE more robust in capturing extreme values compared to POD modes.
New method reduces PDE model parameters by 30% with sparsity.
problem Redundant parameters in neural network projections.
method Bregman iterations for sparsity, POD compression, bias propagation.
result 30% fewer parameters with similar accuracy.
Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization methods to tackle this issue. The most prominent algorithm in this line of research is LARS, which by employing layerwise adaptive learning ra…
A new autoencoder combines deep learning with SVD to reduce model complexity.
problem Overcoming the Kolmogorov barrier in high-dimensional systems.
method Learnable weighted hybrid autoencoder combining SVD and deep learning.
result Empirically, the model exhibits a sharpness thousands of times smaller than other models.
We consider the fusion of two aerodynamic data sets originating from differing fidelity physical or computer experiments. We specifically address the fusion of: 1) noisy and in-complete fields from wind tunnel measurements and 2) deterministic but biased fields from numerical simulations. These two data sources are fus…
ProtTrans models predict protein features without evolutionary info.
problem Predicting protein features from amino acid sequences.
method Self-supervised deep learning on large protein datasets.
result ProtT5 embeddings outperform state-of-the-art for per-residue predictions.
Accelerates BERT pretraining from 3 days to 54 minutes.
problem Long training time of BERT due to large mini-batch sizes.
method LANS method and learning rate scheduler for large mini-batch training.
result Achieved fastest BERT training time of 54 minutes.