# Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation

arXiv: https://arxiv.org/abs/2107.04479 · HTML: https://mlsanity.com/paper/2107.04479/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 9 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [On Lazy Training in Differentiable Programming](https://mlsanity.com/paper/1812.07956/) (2018)
- [Gradient Descent Provably Optimizes Over-parameterized Neural Networks](https://mlsanity.com/paper/1810.02054/) (2018)
- [On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport](https://mlsanity.com/paper/1805.09545/) (2018)
- [Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced](https://mlsanity.com/paper/1806.00900/) (2018)
- [Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't](https://mlsanity.com/paper/2009.10713/) (2020)
- [Conservative set valued fields, automatic differentiation, stochastic gradient method and deep learning](https://mlsanity.com/paper/1909.10300/) (2019)
- [Convergence rates for the stochastic gradient descent method for non-convex objective functions](https://mlsanity.com/paper/1904.01517/) (2019)
- [Gradient Descent Quantizes ReLU Network Features](https://mlsanity.com/paper/1803.08367/) (2018)
- [Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers](https://mlsanity.com/paper/1910.05505/) (2019)
- [Sparse Optimization on Measures with Over-parameterized Gradient Descent](https://mlsanity.com/paper/1907.10300/) (2019)
- [A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics](https://mlsanity.com/paper/1904.04326/) (2019)
- [Gradient Dynamics of Shallow Univariate ReLU Networks](https://mlsanity.com/paper/1906.07842/) (2019)
- [Solving the Kolmogorov PDE by means of deep learning](https://mlsanity.com/paper/1806.00421/) (2018)
- [A Dynamical Central Limit Theorem for Shallow Neural Networks](https://mlsanity.com/paper/2008.09623/) (2020)
- [A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions](https://mlsanity.com/paper/2102.09924/) (2021)
- [Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions](https://mlsanity.com/paper/2103.10922/) (2021)
- [A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions](https://mlsanity.com/paper/2104.00277/) (2021)

## Built on by (most cited first, 11 of 11)

- [Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs](https://mlsanity.com/paper/2306.06479/) (2023)
- [A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions](https://mlsanity.com/paper/2108.04620/) (2021)
- [Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation](https://mlsanity.com/paper/2108.08106/) (2021)
- [Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions](https://mlsanity.com/paper/2112.07369/) (2021)
- [Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks](https://mlsanity.com/paper/2402.05155/) (2024)
- [Operator theory, kernels, and Feedforward Neural Networks](https://mlsanity.com/paper/2301.01327/) (2023)
- [Convergence of Shallow ReLU Networks on Weakly Interacting Data](https://mlsanity.com/paper/2502.16977/) (2025)
- [Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization](https://mlsanity.com/paper/2602.13513/) (2026)
- [Normalized gradient flow optimization in the training of ReLU artificial neural networks](https://mlsanity.com/paper/2207.06246/) (2022)
- [Predicting the fatigue life of asphalt concrete using neural networks](https://mlsanity.com/paper/2406.01523/) (2024)
- [Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations](https://mlsanity.com/paper/2510.24466/) (2025)

## Abstract (arXiv)

Gradient descent (GD) type optimization schemes are the standard methods to train artificial neural networks (ANNs) with rectified linear unit (ReLU) activation. Such schemes can be considered as discretizations of gradient flows (GFs) associated to the training of ANNs with ReLU activation and most of the key difficulties in the mathematical convergence analysis of GD type optimization schemes in the training of ANNs with ReLU activation seem to be already present in the dynamics of the corresponding GF differential equations. It is the key subject of this work to analyze such GF differential equations in the training of ANNs with ReLU activation and three layers (one input layer, one hidden layer, and one output layer). In particular, in this article we prove in the case where the target function is possibly multi-dimensional and continuous and in the case where the probability distribution of the input data is absolutely continuous with respect to the Lebesgue measure that the risk of every bounded GF trajectory converges to the risk of a critical point. In addition, in this article we show in the case of a 1-dimensional affine linear target function and in the case where the probability distribution of the input data coincides with the standard uniform distribution that the risk of every bounded GF trajectory converges to zero if the initial risk is sufficiently small. Finally, in the special situation where there is only one neuron on the hidden layer (1-dimensional hidden layer) we strengthen the above named result for affine linear target functions by proving that that the risk of every (not necessarily bounded) GF trajectory converges to zero if the initial risk is sufficiently small.