English
Related papers

Related papers: Approximation results for Gradient Descent trained…

200 papers

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or smoothness, and, in the smooth setting, only guarantee…

Machine Learning · Computer Science 2019-10-22 Xiaoxia Wu , Simon S. Du , Rachel Ward

This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA)…

Machine Learning · Statistics 2017-06-16 Simone Scardapane , Paolo Di Lorenzo

In this work, we present a comprehensive study combining mathematical and computational analysis to explain why a two-layer neural network struggles to handle high frequencies in both approximation and learning, especially when machine…

Machine Learning · Computer Science 2025-06-04 Shijun Zhang , Hongkai Zhao , Yimin Zhong , Haomin Zhou

We perform a comprehensive numerical study of the effect of approximation-theoretical results for neural networks on practical learning problems in the context of numerical analysis. As the underlying model, we study the…

Numerical Analysis · Mathematics 2020-04-28 Moritz Geist , Philipp Petersen , Mones Raslan , Reinhold Schneider , Gitta Kutyniok

The Universal Approximation Theorem posits that neural networks can theoretically possess unlimited approximation capacity with a suitable activation function and a freely chosen or trained set of parameters. However, a more practical…

Machine Learning · Computer Science 2024-09-26 Li Liu , Tengchao Yu , Heng Yong

We analyze the generalization properties of two-layer neural networks in the neural tangent kernel (NTK) regime, trained with gradient descent (GD). For early stopped GD we derive fast rates of convergence that are known to be minimax…

Machine Learning · Statistics 2023-09-18 Mike Nguyen , Nicole Mücke

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

We study multigrade deep learning (MGDL) as a principled framework for structured error refinement in deep neural networks. While the approximation power of neural networks is now relatively well understood, training very deep architectures…

Machine Learning · Computer Science 2026-04-03 Shijun Zhang , Zuowei Shen , Yuesheng Xu

Linear networks provide valuable insights into the workings of neural networks in general. This paper identifies conditions under which the gradient flow provably trains a linear network, in spite of the non-strict saddle points present in…

Optimization and Control · Mathematics 2020-06-30 Armin Eftekhari

In this review paper, we give a comprehensive overview of the large variety of approximation results for neural networks. Approximation rates for classical function spaces as well as benefits of deep neural networks over shallow ones for…

Machine Learning · Computer Science 2020-07-10 Ingo Gühring , Mones Raslan , Gitta Kutyniok

While significant theoretical progress has been achieved, unveiling the generalization mystery of overparameterized neural networks still remains largely elusive. In this paper, we study the generalization behavior of shallow neural…

Machine Learning · Computer Science 2022-09-21 Yunwen Lei , Rong Jin , Yiming Ying

Neural operators are aiming at approximating operators mapping between Banach spaces of functions, achieving much success in the field of scientific computing. Compared to certain deep learning-based solvers, such as Physics-Informed Neural…

Machine Learning · Computer Science 2025-01-13 Xianliang Xu , Ye Li , Zhongyi Huang

We study stochastic optimization of nonconvex loss functions, which are typical objectives for training neural networks. We propose stochastic approximation algorithms which optimize a series of regularized, nonlinearized losses on large…

Machine Learning · Computer Science 2019-03-12 Weiran Wang , Nathan Srebro

Artificial Neuronal Networks are models widely used for many scientific tasks. One of the well-known field of application is the approximation of high-dimensional problems via Deep Learning. In the present paper we investigate the Deep…

Numerical Analysis · Mathematics 2021-10-06 F. Calabrò , S. Cuomo , F. Giampaolo , S. Izzo , C. Nitsch , F. Piccialli , C. Trombetti

Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks. In this paper, we study a fundamental question that arises when designing deep…

Machine Learning · Statistics 2017-10-24 Shiva Prasad Kasiviswanathan , Nina Narodytska , Hongxia Jin

Nonparametric regression with random design is considered. Estimates are defined by minimzing a penalized empirical $L_2$ risk over a suitably chosen class of neural networks with one hidden layer via gradient descent. Here, the gradient…

Statistics Theory · Mathematics 2019-12-10 Alina Braun , Michael Kohler , Harro Walk

Fitting a function by using linear combinations of a large number $N$ of `simple' components is one of the most fruitful ideas in statistical learning. This idea lies at the core of a variety of methods, from two-layer neural networks to…

Statistics Theory · Mathematics 2019-08-20 Adel Javanmard , Marco Mondelli , Andrea Montanari

Neural networks are usually not the tool of choice for nonparametric high-dimensional problems where the number of input features is much larger than the number of observations. Though neural networks can approximate complex multivariate…

Methodology · Statistics 2019-06-25 Jean Feng , Noah Simon

We study the gradient descent (GD) dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize --…

Machine Learning · Computer Science 2025-01-22 Pierfrancesco Beneventano , Blake Woodworth

Data driven classification that relies on neural networks is based on optimization criteria that involve some form of distance between the output of the network and the desired label. Using the same mathematical analysis, for a multitude of…

Machine Learning · Computer Science 2019-06-25 Kalliopi Basioti , George V. Moustakides