# A proof of convergence for gradient descent in the training of artificial neural networks for constant target functions

arXiv: https://arxiv.org/abs/2102.09924 · HTML: https://mlsanity.com/paper/2102.09924/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 27 references that are in the map.
- First posted on arXiv 19 Feb 2021.

## Builds on (most cited first, 22 of 22)

- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [A Convergence Theory for Deep Learning via Over-Parameterization](https://mlsanity.com/paper/1811.03962/) (2018)
- [Gradient Descent Provably Optimizes Over-parameterized Neural Networks](https://mlsanity.com/paper/1810.02054/) (2018)
- [Gradient Descent Finds Global Minima of Deep Neural Networks](https://mlsanity.com/paper/1811.03804/) (2018)
- [On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport](https://mlsanity.com/paper/1805.09545/) (2018)
- [Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers](https://mlsanity.com/paper/1811.04918/) (2018)
- [Breaking the Curse of Dimensionality with Convex Neural Networks](https://mlsanity.com/paper/1412.8690/) (2014)
- [Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data](https://mlsanity.com/paper/1808.01204/) (2018)
- [Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks](https://mlsanity.com/paper/1811.08888/) (2018)
- [Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)](https://mlsanity.com/paper/1306.2119/) (2013)
- [How to Start Training: The Effect of Initialization and Architecture](https://mlsanity.com/paper/1803.01719/) (2018)
- [Which Neural Net Architectures Give Rise To Exploding and Vanishing Gradients?](https://mlsanity.com/paper/1801.03744/) (2018)
- [Convergence rates for the stochastic gradient descent method for non-convex objective functions](https://mlsanity.com/paper/1904.01517/) (2019)
- [Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks](https://mlsanity.com/paper/1902.01384/) (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)
- [Stochastic Gradient Descent for Nonconvex Learning without Bounded Gradient Assumptions](https://mlsanity.com/paper/1902.00908/) (2019)
- [The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent](https://mlsanity.com/paper/1904.06963/) (2019)
- [Collapse of Deep and Narrow Neural Nets](https://mlsanity.com/paper/1808.04947/) (2018)
- [Taming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms](https://mlsanity.com/paper/2006.14514/) (2020)
- [Non-convergence of stochastic gradient descent in the training of deep neural networks](https://mlsanity.com/paper/2006.07075/) (2020)
- [Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization](https://mlsanity.com/paper/2002.05465/) (2020)
- [Lower error bounds for the stochastic gradient descent optimization algorithm: Sharp convergence rates for slowly and fast decaying learning rates](https://mlsanity.com/paper/1803.08600/) (2018)

## Built on by (most cited first, 14 of 14)

- [On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks](https://mlsanity.com/paper/2112.09684/) (2021)
- [Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions](https://mlsanity.com/paper/2103.10922/) (2021)
- [Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation](https://mlsanity.com/paper/2107.04479/) (2021)
- [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)
- [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)
- [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)
- [Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks](https://mlsanity.com/paper/2503.01660/) (2025)
- [Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks](https://mlsanity.com/paper/2206.02139/) (2022)
- [Gradient descent provably escapes saddle points in the training of shallow ReLU networks](https://mlsanity.com/paper/2208.02083/) (2022)
- [Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions](https://mlsanity.com/paper/2506.08234/) (2025)
- [Physics Informed Constrained Learning of Dynamics from Static Data](https://mlsanity.com/paper/2504.12675/) (2025)
- [Normalized gradient flow optimization in the training of ReLU artificial neural networks](https://mlsanity.com/paper/2207.06246/) (2022)

## Abstract (arXiv)

Gradient descent optimization algorithms are the standard ingredients that are used to train artificial neural networks (ANNs). Even though a huge number of numerical simulations indicate that gradient descent optimization methods do indeed convergence in the training of ANNs, until today there is no rigorous theoretical analysis which proves (or disproves) this conjecture. In particular, even in the case of the most basic variant of gradient descent optimization algorithms, the plain vanilla gradient descent method, it remains an open problem to prove or disprove the conjecture that gradient descent converges in the training of ANNs. In this article we solve this problem in the special situation where the target function under consideration is a constant function. More specifically, in the case of constant target functions we prove in the training of rectified fully-connected feedforward ANNs with one-hidden layer that the risk function of the gradient descent method does indeed converge to zero. Our mathematical analysis strongly exploits the property that the rectifier function is the activation function used in the considered ANNs. A key contribution of this work is to explicitly specify a Lyapunov function for the gradient flow system of the ANN parameters. This Lyapunov function is the central tool in our convergence proof of the gradient descent method.