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

arXiv: https://arxiv.org/abs/2005.12564 · HTML: https://mlsanity.com/paper/2005.12564/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2020.

## Built on by (most cited first, 20 of 20)

- [On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology](https://mlsanity.com/paper/2302.02941/) (2023)
- [On the approximation of functions by tanh neural networks](https://mlsanity.com/paper/2104.08938/) (2021)
- [Error estimates for physics informed neural networks approximating the Navier-Stokes equations](https://mlsanity.com/paper/2203.09346/) (2022)
- [wPINNs: Weak Physics informed neural networks for approximating entropy solutions of hyperbolic conservation laws](https://mlsanity.com/paper/2207.08483/) (2022)
- [A Deep Learning approach to Reduced Order Modelling of Parameter Dependent Partial Differential Equations](https://mlsanity.com/paper/2103.06183/) (2021)
- [NeuFENet: Neural Finite Element Solutions with Theoretical Bounds for Parametric PDEs](https://mlsanity.com/paper/2110.01601/) (2021)
- [On the Generalization of PINNs outside the training domain and the Hyperparameters influencing it](https://mlsanity.com/paper/2302.07557/) (2023)
- [A practical existence theorem for reduced order models based on convolutional autoencoders](https://mlsanity.com/paper/2402.00435/) (2024)
- [Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks](https://mlsanity.com/paper/2405.15059/) (2024)
- [Physics-aware deep neural networks for surrogate modeling of turbulent natural convection](https://mlsanity.com/paper/2103.03565/) (2021)
- [Lattice-based Deep Neural Networks: Regularity and Tailored Regularization](https://mlsanity.com/paper/2603.02809/) (2026)
- [Convergence analysis of a quasi-Monte Carlo-based deep learning algorithm for solving partial differential equations](https://mlsanity.com/paper/2210.16196/) (2022)
- [Error Analysis of Physics-Informed Neural Networks for Approximating Dynamic PDEs of Second Order in Time](https://mlsanity.com/paper/2303.12245/) (2023)
- [Using Low-Discrepancy Points for Data Compression in Machine Learning: An Experimental Comparison](https://mlsanity.com/paper/2407.07450/) (2024)
- [Neural Low-Discrepancy Sequences](https://mlsanity.com/paper/2510.03745/) (2025)
- [Toward High-Performance Energy and Power Battery Cells with Machine Learning-based Optimization of Electrode Manufacturing](https://mlsanity.com/paper/2307.05521/) (2023)
- [A Bayesian Approach to Low-Discrepancy Subset Selection](https://mlsanity.com/paper/2602.14607/) (2026)
- [Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization](https://mlsanity.com/paper/2603.28040/) (2026)
- [Fourier Neural Operators with rank-1 lattice points and hyperbolic cross](https://mlsanity.com/paper/2606.08871/) (2026)
- [High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube](https://mlsanity.com/paper/2608.26526/) (2026)

## Abstract (arXiv)

We propose a deep supervised learning algorithm based on low-discrepancy sequences as the training set. By a combination of theoretical arguments and extensive numerical experiments we demonstrate that the proposed algorithm significantly outperforms standard deep learning algorithms that are based on randomly chosen training data, for problems in moderately high dimensions. The proposed algorithm provides an efficient method for building inexpensive surrogates for many underlying maps in the context of scientific computing.