On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “multiphysics”

Additive Multi-Index Gaussian process modeling, with application to multi-physics surrogate modeling of the quark-gluon plasmanucl-th

New model improves QGP simulation efficiency and accuracy.

problem Limited QGP simulation runs due to high computational cost.

method Additive Multi-Index Gaussian process (AdMIn-GP) model.

result Significantly improved surrogate modeling performance.

Quark-Gluon Plasma Surrogate Modeling Gaussian Process Bayesian Nonparametric Multiphysics

2023-06-11abs ↗pdf ↗

When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?cs.LG

XPINNs improve generalization by decomposing PDEs but may overfit.

problem Understanding when XPINNs outperform PINNs in generalization.

method Theoretical bounds and empirical validation.

result XPINNs improve generalization by decomposing complex PDEs but may overfit.

Physics-informed neural networks generalization multi-scale multiphysics domain decomposition

2021-09-20abs ↗pdf ↗

Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledgecs.LG

Enhances neural operators with physics knowledge for more accurate simulations.

problem Improving accuracy and generalization of neural operators for physical systems.

method Jointly learns from original PDEs and simplified forms, incorporating fundamental physics.

result Significant improvement in nRMSE across various PDE problems.

Neural Operators Scientific Machine Learning Fundamental Physics Data Efficiency Generalization

2026-02-16abs ↗pdf ↗

Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphscs.LG

Method learns Dirichlet-to-Neumann maps on graphs using Gaussian processes.

problem Coupling multiphysics simulations on graphs with conservation constraints.

method Gaussian processes combined with discrete exterior calculus and maximum likelihood estimation.

result Data-driven predictions with uncertainty quantification on entire graph.

Dirichlet-to-Neumann maps graphs Gaussian processes discrete exterior calculus conservation laws

2025-06-03abs ↗pdf ↗

GINNs: Graph-Informed Neural Networks for Multiscale Physicsphysics.comp-ph

GINNs combine deep learning with PGMs for physics-based multiscale systems.

problem Intrinsic computational bottlenecks and lack of sufficient data for QoI estimation.

method Hybrid approach combining deep learning with probabilistic graphical models, informed by structured priors for CVs.

result GINNs produce tight confidence intervals for non-Gaussian QoIs.

Graph-Informed Neural Networks Physics-informed surrogate models Multiscale systems Quantities of interest Confidence intervals

2020-06-26abs ↗pdf ↗

Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transportcs.LG

Data assimilation for parameter and state estimation in subsurface transport problems remains a significant challenge due to the sparsity of measurements, the heterogeneity of porous media, and the high computational cost of forward numerical models. We present a physics-informed deep neural networks (DNNs) machine lea…

2019-12-06abs ↗pdf ↗

Knowledge-based Deep Learning for Modeling Chaotic Systemscs.LG

Deep learning models learn chaotic system dynamics from real and simulated data.

problem Training deep learning models for chaotic systems requires big data.

method Jointly train deep neural networks on real and simulated data, enforcing physical laws.

result Proposes knowledge-based deep learning (KDL) for accurate forecasting of chaotic systems.

chaotic systems deep learning extreme events differential equations neural networks

2022-09-09abs ↗pdf ↗

Fast and Accurate Reduced-Order Modeling of a MOOSE-based Additive Manufacturing Model with Operator Learningcs.LG

This work develops fast and accurate ROMs for AM models using OL methods.

problem Achieving specific material properties in AM by manipulating process parameters increases computational load.

method Operator learning (OL) approach with Fourier neural operator (FNO) and DeepONet.

result OL methods offer comparable performance and outperform DNN in accuracy and generalizability.

reduced-order modeling operator learning additive manufacturing Fourier neural operator DeepONet

2023-08-04abs ↗pdf ↗