Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences

26 May 2020

Papers citing "Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences"

22 / 22 papers shown

Title
Using Low-Discrepancy Points for Data Compression in Machine Learning: An Experimental Comparison Simone Göttlich Jacob Heieck Andreas Neuenkirch 26 0 0 10 Jul 2024
Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks T. Konstantin Rusch Nathan Kirk M. Bronstein Christiane Lemieux Daniela Rus 27 6 0 23 May 2024
A practical existence theorem for reduced order models based on convolutional autoencoders N. R. Franco Simone Brugiapaglia AI4CE 31 4 0 01 Feb 2024
Toward High-Performance Energy and Power Battery Cells with Machine Learning-based Optimization of Electrode Manufacturing M. Duquesnoy C. Liu Vishank Kumar E. Ayerbe A. Franco 23 2 0 07 Jul 2023
Error Analysis of Physics-Informed Neural Networks for Approximating Dynamic PDEs of Second Order in Time Y. Qian Yongchao Zhang Yuanfei Huang S. Dong PINN 21 1 0 22 Mar 2023
On the Generalization of PINNs outside the training domain and the Hyperparameters influencing it Andrea Bonfanti Roberto Santana M. Ellero Babak Gholami AI4CE PINN 43 3 0 15 Feb 2023
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology Francesco Di Giovanni Lorenzo Giusti Federico Barbero Giulia Luise Pietro Lio Michael M. Bronstein 48 112 0 06 Feb 2023
Convergence analysis of a quasi-Monte Carlo-based deep learning algorithm for solving partial differential equations Fengjiang Fu Xiaoqun Wang 29 2 0 28 Oct 2022
wPINNs: Weak Physics informed neural networks for approximating entropy solutions of hyperbolic conservation laws Tim De Ryck Siddhartha Mishra Roberto Molinaro PINN 32 28 0 18 Jul 2022
Error estimates for physics informed neural networks approximating the Navier-Stokes equations Tim De Ryck Ameya Dilip Jagtap S. Mishra PINN 49 115 0 17 Mar 2022
NeuFENet: Neural Finite Element Solutions with Theoretical Bounds for Parametric PDEs Biswajit Khara Aditya Balu Ameya Joshi S. Sarkar C. Hegde A. Krishnamurthy Baskar Ganapathysubramanian 31 19 0 04 Oct 2021
On the approximation of functions by tanh neural networks Tim De Ryck S. Lanthaler Siddhartha Mishra 26 138 0 18 Apr 2021
A Deep Learning approach to Reduced Order Modelling of Parameter Dependent Partial Differential Equations N. R. Franco Andrea Manzoni P. Zunino 26 45 0 10 Mar 2021
Physics-aware deep neural networks for surrogate modeling of turbulent natural convection Didier Lucor A. Agrawal A. Sergent PINN AI4CE 19 16 0 05 Mar 2021
Consequences of Slow Neural Dynamics for Incremental Learning Shima Rahimi Moghaddam Fanjun Bu C. Honey OOD AI4CE 25 0 0 12 Dec 2020
Physics Informed Neural Networks for Simulating Radiative Transfer Siddhartha Mishra Roberto Molinaro PINN 18 103 0 25 Sep 2020
Higher-order Quasi-Monte Carlo Training of Deep Neural Networks M. Longo Suman Mishra T. Konstantin Rusch Christoph Schwab 35 20 0 06 Sep 2020
Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks K. Lye Siddhartha Mishra Deep Ray P. Chandrasekhar 18 75 0 13 Aug 2020
Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions Philipp Grohs L. Herrmann 30 52 0 10 Jul 2020
Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating a class of inverse problems for PDEs Siddhartha Mishra Roberto Molinaro PINN 16 262 0 29 Jun 2020
Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs Siddhartha Mishra Roberto Molinaro PINN 25 171 0 29 Jun 2020
A Multi-level procedure for enhancing accuracy of machine learning algorithms K. Lye Siddhartha Mishra Roberto Molinaro 17 32 0 20 Sep 2019