Searcharxiv⌕ Search

arXiv subjects

Adrian Riekert

Publications and source records attributed to Adrian Riekert.

At least 19 recordsLinked to original sources
arXiv2025

Asymptotic stability properties and a priori bounds for Adam and other gradient descent optimization methods

Gradient descent (GD) based optimization methods are these days the standard tools to train deep neural networks in artificial intelligence systems. In optimization procedures in deep learning the employed optimizer is often not the standard GD method but instead suitable adaptive and accelerated variants of standard GD (including the momentum and the root mean square propagation (RMSprop) optimizers) are considered. The adaptive moment estimation (Adam) optimizer proposed in 2014 by Kingma & Ba is presumably the most popular variant of such adaptive and accelerated GD based optimization methods. Despite the popularity of such sophisticated optimization methods, it remains a fundamental open problem of research to provide a rigorous mathematical analysis for such accelerated and adaptive optimization methods. In particular, it remains an open problem of research to establish boundedness of the Adam optimizer. In this work we solve this problem in the case of a simple class of quadratic strongly convex stochastic optimization problems. Specifically, for the considered class of stochastic optimization problems we reveal a priori bounds for momentum, RMSprop, and Adam. In particular, we prove for the considered class of strongly convex stochastic optimization problems, for the first time, that Adam does not explode but stays bounded for any choices of the learning rates. In this work we also introduce certain stability concepts - such as the notion of the stability region - for deep learning optimizers and we discover that among standard GD, momentum, RMSprop, and Adam we have that Adam is the only optimizer that achieves the optimal higher order convergence speed and also has the maximal stability region.

math.OC↗
arXiv2025

PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning

Averaging techniques such as Ruppert--Polyak averaging and exponential movering averaging (EMA) are powerful approaches to accelerate optimization procedures of stochastic gradient descent (SGD) optimization methods such as the popular ADAM optimizer. However, depending on the specific optimization problem under consideration, the type and the parameters for the averaging need to be adjusted to achieve the smallest optimization error. In this work we propose an averaging approach, which we refer to as parallel averaged ADAM (PADAM), in which we compute parallely different averaged variants of ADAM and during the training process dynamically select the variant with the smallest optimization error. A central feature of this approach is that this procedure requires no more gradient evaluations than the usual ADAM optimizer as each of the averaged trajectories relies on the same underlying ADAM trajectory and thus on the same underlying gradients. We test the proposed PADAM optimizer in 13 stochastic optimization and deep neural network (DNN) learning problems and compare its performance with known optimizers from the literature such as standard SGD, momentum SGD, Adam with and without EMA, and ADAMW. In particular, we apply the compared optimizers to physics-informed neural network, deep Galerkin, deep backward stochastic differential equation and deep Kolmogorov approximations for boundary value partial differential equation problems from scientific machine learning, as well as to DNN approximations for optimal control and optimal stopping problems. In nearly all of the considered examples PADAM achieves, sometimes among others and sometimes exclusively, essentially the smallest optimization error. This work thus strongly suggest to consider PADAM for scientific machine learning problems and also motivates further research for adaptive averaging procedures within the training of DNNs.

math.OC↗
arXiv2025

Sharp higher order convergence rates for the Adam optimizer

Gradient descent based optimization methods are the methods of choice to train deep neural networks in machine learning. Beyond the standard gradient descent method, also suitable modified variants of standard gradient descent involving acceleration techniques such as the momentum method and/or adaptivity techniques such as the RMSprop method are frequently considered optimization methods. These days the most popular of such sophisticated optimization schemes is presumably the Adam optimizer that has been proposed in 2014 by Kingma and Ba. A highly relevant topic of research is to investigate the speed of convergence of such optimization methods. In particular, in 1964 Polyak showed that the standard gradient descent method converges in a neighborhood of a strict local minimizer with rate (x - 1)(x + 1)^{-1} while momentum achieves the (optimal) strictly faster convergence rate (\sqrt{x} - 1)(\sqrt{x} + 1)^{-1} where x \in (1,\infty) is the condition number (the ratio of the largest and the smallest eigenvalue) of the Hessian of the objective function at the local minimizer. It is the key contribution of this work to reveal that Adam also converges with the strictly faster convergence rate (\sqrt{x} - 1)(\sqrt{x} + 1)^{-1} while RMSprop only converges with the convergence rate (x - 1)(x + 1)^{-1}.

math.OC↗
arXiv2025

Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks

Despite the omnipresent use of stochastic gradient descent (SGD) optimization methods in the training of deep neural networks (DNNs), it remains, in basically all practically relevant scenarios, a fundamental open problem to provide a rigorous theoretical explanation for the success (and the limitations) of SGD optimization methods in deep learning. In particular, it remains an open question to prove or disprove convergence of the true risk of SGD optimization methods to the optimal true risk value in the training of DNNs. In one of the main results of this work we reveal for a general class of activations, loss functions, random initializations, and SGD optimization methods (including, for example, standard SGD, momentum SGD, Nesterov accelerated SGD, Adagrad, RMSprop, Adadelta, Adam, Adamax, Nadam, Nadamax, and AMSGrad) that in the training of any arbitrary fully-connected feedforward DNN it does not hold that the true risk of the considered optimizer converges in probability to the optimal true risk value. Nonetheless, the true risk of the considered SGD optimization method may very well converge to a strictly suboptimal true risk value.

cs.LG↗
arXiv2025

Averaged Adam accelerates stochastic optimization in the training of deep neural network approximations for partial differential equation and optimal control problems

Deep learning methods - usually consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays omnipresent in data-driven learning problems as well as in scientific computing tasks such as optimal control (OC) and partial differential equation (PDE) problems. In practically relevant learning tasks, often not the plain-vanilla standard SGD optimization method is employed to train the considered class of DNNs but instead more sophisticated adaptive and accelerated variants of the standard SGD method such as the popular Adam optimizer are used. Inspired by the classical Polyak-Ruppert averaging approach, in this work we apply averaged variants of the Adam optimizer to train DNNs to approximately solve exemplary scientific computing problems in the form of PDEs and OC problems. We test the averaged variants of Adam in a series of learning problems including physics-informed neural network (PINN), deep backward stochastic differential equation (deep BSDE), and deep Kolmogorov approximations for PDEs (such as heat, Black-Scholes, Burgers, and Allen-Cahn PDEs), including DNN approximations for OC problems, and including DNN approximations for image classification problems (ResNet for CIFAR-10). In each of the numerical examples the employed averaged variants of Adam outperform the standard Adam and the standard SGD optimizers, particularly, in the situation of the scientific machine learning problems. The Python source codes for the numerical experiments associated to this work can be found on GitHub at https://github.com/deeplearningmethods/averaged-adam.

math.OC↗
arXiv2024

An Overview on Machine Learning Methods for Partial Differential Equations: from Physics Informed Neural Networks to Deep Operator Learning

The approximation of solutions of partial differential equations (PDEs) with numerical algorithms is a central topic in applied mathematics. For many decades, various types of methods for this purpose have been developed and extensively studied. One class of methods which has received a lot of attention in recent years are machine learning-based methods, which typically involve the training of artificial neural networks (ANNs) by means of stochastic gradient descent type optimization methods. While approximation methods for PDEs using ANNs have first been proposed in the 1990s they have only gained wide popularity in the last decade with the rise of deep learning. This article aims to provide an introduction to some of these methods and the mathematical theory on which they are based. We discuss methods such as physics-informed neural networks (PINNs) and deep BSDE methods and consider several operator learning approaches.

math.NA↗
arXiv2024

Learning rate adaptive stochastic gradient descent optimization methods: numerical simulations for deep learning methods for partial differential equations and convergence analyses

The standard stochastic gradient descent (SGD) optimization method, as well as adaptive methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (particularly, in the situation of constant learning rates). In practice, human-tuned deterministic learning rate schedules or small constant learning rates are often used, and implementations in machine learning frameworks like Tensorflow and Pytorch typically employ constant learning rates. We propose a learning-rate-adaptive approach for SGD methods, adjusting the learning rate based on empirical estimates for the objective function values. Specifically, we propose a learning-rate-adaptive variant of the Adam optimizer and implement it for several machine learning problems, including deep learning methods for partial differential equations such as deep Kolmogorov methods, physics-informed neural networks, and deep Ritz methods. We refer to https://github.com/deeplearningmethods/adaptive-learning-rate for the Python source codes for the numerical simulations in this work. Our results show that the proposed adaptive Adam variant achieves faster reductions of the objective function value compared to Adam with default learning rates. For certain quadratic minimization problems, we rigorously prove that an adaptive SGD variant converges to the global minimizer. This proof uses properties of invariant measures of the SGD dynamics and a generalized convergence analysis for SGD with random predictable learning rates which we develop in this work.

math.OC↗
arXiv2024

Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks

Stochastic gradient descent (SGD) optimization methods such as the plain vanilla SGD method and the popular Adam optimizer are nowadays the method of choice in the training of artificial neural networks (ANNs). Despite the remarkable success of SGD methods in the ANN training in numerical simulations, it remains in essentially all practical relevant scenarios an open problem to rigorously explain why SGD methods seem to succeed to train ANNs. In particular, in most practically relevant supervised learning problems, it seems that SGD methods do with high probability not converge to global minimizers in the optimization landscape of the ANN training problem. Nevertheless, it remains an open problem of research to disprove the convergence of SGD methods to global minimizers. In this work we solve this research problem in the situation of shallow ANNs with the rectified linear unit (ReLU) and related activations with the standard mean square error loss by disproving in the training of such ANNs that SGD methods (such as the plain vanilla SGD, the momentum SGD, the AdaGrad, the RMSprop, and the Adam optimizers) can find a global minimizer with high probability. Even stronger, we reveal in the training of such ANNs that SGD methods do with high probability fail to converge to global minimizers in the optimization landscape. The findings of this work do, however, not disprove that SGD methods succeed to train ANNs since they do not exclude the possibility that SGD methods find good local minimizers whose risk values are close to the risk values of the global minimizers. In this context, another key contribution of this work is to establish the existence of a hierarchical structure of local minimizers with distinct risk values in the optimization landscape of ANN training problems with ReLU and related activations.

math.OC↗
arXiv2023

Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions

In many numerical simulations stochastic gradient descent (SGD) type optimization methods perform very effectively in the training of deep neural networks (DNNs) but till this day it remains an open problem of research to provide a mathematical convergence analysis which rigorously explains the success of SGD type optimization methods in the training of DNNs. In this work we study SGD type optimization methods in the training of fully-connected feedforward DNNs with rectified linear unit (ReLU) activation. We first establish general regularity properties for the risk functions and their generalized gradient functions appearing in the training of such DNNs and, thereafter, we investigate the plain vanilla SGD optimization method in the training of such DNNs under the assumption that the target function under consideration is a constant function. Specifically, we prove under the assumption that the learning rates (the step sizes of the SGD optimization method) are sufficiently small but not $L^1$-summable and under the assumption that the target function is a constant function that the expectation of the riskof the considered SGD process converges in the training of such DNNs to zero as the number of SGD steps increases to infinity.

cs.LG↗
arXiv2023

A proof of the corrected Sister Beiter cyclotomic coefficient conjecture inspired by Zhao and Zhang

The largest coefficient (in absolute value) of a cyclotomic polynomial $Φ_n$ is called its height $A(n)$. In case $p$ is a fixed prime it turns out that as $q$ and $r$ range over all primes satisfying $p<q<r$, the height $A(pqr)$ assumes a maximum $M(p)$. In 1968, Sister Marion Beiter conjectured that $M(p)\leq (p+1)/2$. In 2009, this was disproved for every $p\ge 11$ by Yves Gallot and Pieter Moree. They proposed a Corrected Beiter Conjecture, namely $M(p)\leq 2p/3$. In 2009, Jia Zhao and Xianke Zhang posted on the arXiv what they thought to be a proof of this conjecture. Their work was never accepted for publication in a journal. However, in retrospect it turns out to be essentially correct, but rather sketchy at some points. Here we supply a lot more details. \par The bound $M(p)\le 2p/3$ allows us to improve some bounds of Bzdęga from 2010 for ternary cyclotomic coefficients. It also makes it possible to determine $M(p)$ exactly for three new primes $p$ and study the fine structure of $A(pqr)$ for them in greater detail.

math.NT↗
arXiv2023

Deep neural network approximation of composite functions without the curse of dimensionality

In this article we identify a general class of high-dimensional continuous functions that can be approximated by deep neural networks (DNNs) with the rectified linear unit (ReLU) activation without the curse of dimensionality. In other words, the number of DNN parameters grows at most polynomially in the input dimension and the approximation error. The functions in our class can be expressed as a potentially unbounded number of compositions of special functions which include products, maxima, and certain parallelized Lipschitz continuous functions.

math.NA↗
arXiv2023

Algorithmically Designed Artificial Neural Networks (ADANNs): Higher order deep operator learning for parametric partial differential equations

In this article we propose a new deep learning approach to approximate operators related to parametric partial differential equations (PDEs). In particular, we introduce a new strategy to design specific artificial neural network (ANN) architectures in conjunction with specific ANN initialization schemes which are tailor-made for the particular approximation problem under consideration. In the proposed approach we combine efficient classical numerical approximation techniques with deep operator learning methodologies. Specifically, we introduce customized adaptions of existing ANN architectures together with specialized initializations for these ANN architectures so that at initialization we have that the ANNs closely mimic a chosen efficient classical numerical algorithm for the considered approximation problem. The obtained ANN architectures and their initialization schemes are thus strongly inspired by numerical algorithms as well as by popular deep learning methodologies from the literature and in that sense we refer to the introduced ANNs in conjunction with their tailor-made initialization schemes as Algorithmically Designed Artificial Neural Networks (ADANNs). We numerically test the proposed ADANN methodology in the case of several parametric PDEs. In the tested numerical examples the ADANN methodology significantly outperforms existing classical approximation algorithms as well as existing deep operator learning methodologies from the literature.

math.NA↗
arXiv2022

Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global local minima with high probability

Gradient descent (GD) methods for the training of artificial neural networks (ANNs) belong nowadays to the most heavily employed computational schemes in the digital world. Despite the compelling success of such methods, it remains an open problem to provide a rigorous theoretical justification for the success of GD methods in the training of ANNs. The main difficulty is that the optimization risk landscapes associated to ANNs usually admit many non-optimal critical points (saddle points as well as non-global local minima) whose risk values are strictly larger than the optimal risk value. It is a key contribution of this article to overcome this obstacle in certain simplified shallow ANN training situations. In such simplified ANN training scenarios we prove that the gradient flow (GF) dynamics with only one random initialization overcomes with high probability all bad non-global local minima (all non-global local minima whose risk values are much larger than the risk value of the global minima) and converges with high probability to a good critical point (a critical point whose risk value is very close to the optimal risk value of the global minima). This analysis allows us to establish convergence in probability to zero of the risk value of the GF trajectories with convergence rates as the ANN training time and the width of the ANN increase to infinity. We complement the analytical findings of this work with extensive numerical simulations for shallow and deep ANNs: All these numerical simulations strongly suggest that with high probability the considered GD method (stochastic GD or Adam) overcomes all bad non-global local minima, does not converge to a global minimum, but does converge to a good non-optimal critical point whose risk value is very close to the optimal risk value.

math.OC↗
arXiv2022

Convergence Rates for Empirical Measures of Markov Chains in Dual and Wasserstein Distances

We consider a Markov chain on $\mathbb{R}^d$ with invariant measure $μ$. We are interested in the rate of convergence of the empirical measures towards the invariant measure with respect to various dual distances, including in particular the $1$-Wasserstein distance. The main result of this article is a new upper bound for the expected distance, which is proved by combining a Fourier expansion with a truncation argument. Our bound matches the known rates for i.i.d. random variables up to logarithmic factors. In addition, we show how concentration inequalities around the mean can be obtained.

math.PR↗
arXiv2022

Normalized gradient flow optimization in the training of ReLU artificial neural networks

The training of artificial neural networks (ANNs) is nowadays a highly relevant algorithmic procedure with many applications in science and industry. Roughly speaking, ANNs can be regarded as iterated compositions between affine linear functions and certain fixed nonlinear functions, which are usually multidimensional versions of a one-dimensional so-called activation function. The most popular choice of such a one-dimensional activation function is the rectified linear unit (ReLU) activation function which maps a real number to its positive part $ \mathbb{R} \ni x \mapsto \max\{ x, 0 \} \in \mathbb{R} $. In this article we propose and analyze a modified variant of the standard training procedure of such ReLU ANNs in the sense that we propose to restrict the negative gradient flow dynamics to a large submanifold of the ANN parameter space, which is a strict $ C^{ \infty } $-submanifold of the entire ANN parameter space that seems to enjoy better regularity properties than the entire ANN parameter space but which is also sufficiently large and sufficiently high dimensional so that it can represent all ANN realization functions that can be represented through the entire ANN parameter space. In the special situation of shallow ANNs with just one-dimensional ANN layers we also prove for every Lipschitz continuous target function that every gradient flow trajectory on this large submanifold of the ANN parameter space is globally bounded. For the standard gradient flow on the entire ANN parameter space with Lipschitz continuous target functions it remains an open problem of research to prove or disprove the global boundedness of gradient flow trajectories even in the situation of shallow ANNs with just one-dimensional ANN layers.

math.OC↗
arXiv2022

On the existence of global minima and convergence analyses for gradient descent methods in the training of deep neural networks

In this article we study fully-connected feedforward deep ReLU ANNs with an arbitrarily large number of hidden layers and we prove convergence of the risk of the GD optimization method with random initializations in the training of such ANNs under the assumption that the unnormalized probability density function of the probability distribution of the input data of the considered supervised learning problem is piecewise polynomial, under the assumption that the target function (describing the relationship between input data and the output data) is piecewise polynomial, and under the assumption that the risk function of the considered supervised learning problem admits at least one regular global minimum. In addition, in the special situation of shallow ANNs with just one hidden layer and one-dimensional input we also verify this assumption by proving in the training of such shallow ANNs that for every Lipschitz continuous target function there exists a global minimum in the risk landscape. Finally, in the training of deep ANNs with ReLU activation we also study solutions of gradient flow (GF) differential equations and we prove that every non-divergent GF trajectory converges with a polynomial rate of convergence to a critical point (in the sense of limiting Fréchet subdifferentiability). Our mathematical convergence analysis builds up on ideas from our previous article Eberle et al., on tools from real algebraic geometry such as the concept of semi-algebraic functions and generalized Kurdyka-Lojasiewicz inequalities, on tools from functional analysis such as the Arzelà-Ascoli theorem, on tools from nonsmooth analysis such as the concept of limiting Fréchet subgradients, as well as on the fact that the set of realization functions of shallow ReLU ANNs with fixed architecture forms a closed subset of the set of continuous functions revealed by Petersen et al.

math.OC↗
arXiv2022

On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation

Gradient descent (GD) type optimization schemes are the standard instruments to train fully connected feedforward artificial neural networks (ANNs) with rectified linear unit (ReLU) activation and can be considered as temporal discretizations of solutions of gradient flow (GF) differential equations. It has recently been proved that the risk of every bounded GF trajectory converges in the training of ANNs with one hidden layer and ReLU activation to the risk of a critical point. Taking this into account it is one of the key research issues in the mathematical convergence analysis of GF trajectories and GD type optimization schemes, respectively, to study sufficient and necessary conditions for critical points of the risk function and, thereby, to obtain an understanding about the appearance of critical points in dependence of the problem parameters such as the target function. In the first main result of this work we prove in the training of ANNs with one hidden layer and ReLU activation that for every $ a, b \in \mathbb{R} $ with $ a < b $ and every arbitrarily large $ δ> 0 $ we have that there exists a Lipschitz continuous target function $ f \colon [a,b] \to \mathbb{R} $ such that for every number $ H > 1 $ of neurons on the hidden layer we have that the risk function has uncountably many different realization functions of non-global local minimum points whose risks are strictly larger than the sum of the risk of the global minimum points and the arbitrarily large $ δ$. In the second main result of this work we show in the training of ANNs with one hidden layer and ReLU activation in the special situation where there is only one neuron on the hidden layer and where the target function is continuous and piecewise polynomial that there exist at most finitely many different realization functions of critical points.

math.OC↗
arXiv2021

Existence, uniqueness, and convergence rates for gradient flows in the training of artificial neural networks with ReLU activation

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. Till this day in the scientific literature there is in general no mathematical convergence analysis which explains the numerical success of GD type optimization schemes in the training of ANNs with ReLU activation. GD type optimization schemes can be regarded as temporal discretization methods for the gradient flow (GF) differential equations associated to the considered optimization problem and, in view of this, it seems to be a natural direction of research to first aim to develop a mathematical convergence theory for time-continuous GF differential equations and, thereafter, to aim to extend such a time-continuous convergence theory to implementable time-discrete GD type optimization methods. In this article we establish two basic results for GF differential equations in the training of fully-connected feedforward ANNs with one hidden layer and ReLU activation. In the first main result of this article we establish in the training of such ANNs under the assumption that the probability distribution of the input data of the considered supervised learning problem is absolutely continuous with a bounded density function that every GF differential equation admits for every initial value a solution which is also unique among a suitable class of solutions. In the second main result of this article we prove in the training of such ANNs under the assumption that the target function and the density function of the probability distribution of the input data are piecewise polynomial that every non-divergent GF trajectory converges with an appropriate rate of convergence to a critical point and that the risk of the non-divergent GF trajectory converges with rate 1 to the risk of the critical point.

cs.LG↗