English
Related papers

Related papers: Curse of Dimensionality in Neural Network Optimiza…

200 papers

Deep neural network (DNN) usually learns the target function from low to high frequency, which is called frequency principle or spectral bias. This frequency principle sheds light on a high-frequency curse of DNNs -- difficult to learn…

Machine Learning · Computer Science 2022-08-23 Tao Luo , Zheng Ma , Zhiwei Wang , Zhi-Qin John Xu , Yaoyu Zhang

We consider neural networks with a single hidden layer and non-decreasing homogeneous activa-tion functions like the rectified linear units. By letting the number of hidden units grow unbounded and using classical non-Euclidean…

Machine Learning · Computer Science 2016-11-01 Francis Bach

We offer a theoretical validation of the curse of dimensionality in the pivot-based indexing of datasets for similarity search, by proving, in the framework of statistical learning, that in high dimensions no pivot-based indexing scheme can…

Data Structures and Algorithms · Computer Science 2016-11-17 Ilya Volnyansky , Vladimir Pestov

This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training dynamics. Our analysis provides evidence for BTH by relating…

Machine Learning · Computer Science 2021-11-01 Andreas Loukas , Marinos Poiitis , Stefanie Jegelka

Diffusion models are state-of-the-art tools for various generative tasks. Yet training these models involves estimating high-dimensional score functions, which in principle suffers from the curse of dimensionality. It is therefore important…

Machine Learning · Computer Science 2025-09-30 Georg A. Gottwald , Shuigen Liu , Youssef Marzouk , Sebastian Reich , Xin T. Tong

Due to their susceptibility to adversarial perturbations, neural networks (NNs) are hardly used in safety-critical applications. One measure of robustness to such perturbations in the input is the Lipschitz constant of the input-output map…

Machine Learning · Computer Science 2021-04-30 Patricia Pauli , Anne Koch , Julian Berberich , Paul Kohler , Frank Allgöwer

Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good…

Machine Learning · Computer Science 2020-05-26 Wesley J. Maddox , Gregory Benton , Andrew Gordon Wilson

Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout rate. Arguably, the learning rate is the most important of…

Machine Learning · Computer Science 2020-08-04 Rahul Yedida , Snehanshu Saha , Tejas Prashanth

We investigate the stochastic optimization problem of minimizing population risk, where the loss defining the risk is assumed to be weakly convex. Compositions of Lipschitz convex functions with smooth maps are the primary examples of such…

Optimization and Control · Mathematics 2018-12-19 Damek Davis , Dmitriy Drusvyatskiy

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

In this paper we consider PIDEs with gradient-independent Lipschitz continuous nonlinearities and prove that deep neural networks with ReLU activation function can approximate solutions of such semilinear PIDEs without curse of…

Numerical Analysis · Mathematics 2025-01-22 Ariel Neufeld , Tuan Anh Nguyen , Sizhou Wu

We study the training dynamics of a shallow neural network with quadratic activation functions and quadratic cost in a teacher-student setup. In line with previous works on the same neural architecture, the optimization is performed…

Optimization and Control · Mathematics 2023-11-08 Simon Martin , Francis Bach , Giulio Biroli

Neural networks are commonly trained in highly overparameterized regimes, yet empirical evidence consistently shows that many parameters become redundant during learning. Most existing pruning approaches impose sparsity through explicit…

Neural and Evolutionary Computing · Computer Science 2026-01-19 Zubair Shah , Noaman Khan

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by computing a global bound on its Lipschitz constant.…

Machine Learning · Computer Science 2021-11-03 Yujia Huang , Huan Zhang , Yuanyuan Shi , J Zico Kolter , Anima Anandkumar

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Deep continual learning requires models to adapt to new tasks without retraining from scratch. However, neural networks can lose their ability to adapt to new tasks after training on previous ones, a phenomenon known as loss of plasticity.…

Machine Learning · Computer Science 2026-05-12 Jiuqi Wang , Jayanth Srinivasa , Claire Chen , Shuze Daniel Liu , Ali Payani , Shangtong Zhang

The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varying comparators. In the…

Machine Learning · Computer Science 2022-02-28 Nima Eshraghi , Ben Liang

We study two factors in neural network training: data parallelism and sparsity; here, data parallelism means processing training data in parallel using distributed systems (or equivalently increasing batch size), so that training can be…

Machine Learning · Computer Science 2021-04-05 Namhoon Lee , Thalaiyasingam Ajanthan , Philip H. S. Torr , Martin Jaggi

A regression problem with dependent data is considered. Regularity assumptions on the dependency of the data are introduced, and it is shown that under suitable structural assumptions on the regression function a deep recurrent neural…

Machine Learning · Statistics 2020-11-03 Michael Kohler , Adam Krzyzak

Deep learning has non-convex loss landscape and its optimization dynamics is hard to analyze or control. Nevertheless, the dynamics can be empirically convex-like across various tasks, models, optimizers, hyperparameters, etc. In this work,…

Machine Learning · Computer Science 2026-02-10 Zhiqi Bu , Shiyun Xu , Jialin Mao