English
Related papers

Related papers: Curse of Dimensionality in Neural Network Optimiza…

200 papers

We propose a novel algorithm for combined unit and layer pruning of deep neural networks that functions during training and without requiring a pre-trained network to apply. Our algorithm optimally trades-off learning accuracy and pruning…

Machine Learning · Computer Science 2025-07-17 Valentin Frank Ingmar Guenter , Athanasios Sideris

We present a theoretical and experimental investigation of the quantization problem for artificial neural networks. We provide a mathematical definition of quantized neural networks and analyze their approximation capabilities, showing in…

Machine Learning · Computer Science 2019-05-29 Matteo Spallanzani , Lukas Cavigelli , Gian Paolo Leonardi , Marko Bertogna , Luca Benini

On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is…

Machine Learning · Statistics 2024-06-25 Blake Bordelon , Alexander Atanasov , Cengiz Pehlevan

Randomized smoothing is a widely adopted technique for optimizing nonsmooth objective functions. However, its efficiency analysis typically relies on global Lipschitz continuity, a condition rarely met in practical applications. To address…

Optimization and Control · Mathematics 2025-09-10 Jingfan Xia , Zhenwei Lin , Qi Deng

It is generally assumed that the brain uses something akin to sparse distributed representations. These representations, however, are high-dimensional and consequently they affect classification performance of traditional Machine Learning…

Neural and Evolutionary Computing · Computer Science 2022-08-29 Maria Osório , Luís Sa-Couto , Andreas Wichert

We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Tiffany Vlaar , Timothée Pouchon , Amos Storkey

The widespread adoption of deep learning models places demands on their robustness. In this paper, we consider the robustness of deep neural networks on videos, which comprise both the spatial features of individual frames extracted by a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Min Wu , Marta Kwiatkowska

Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks. One crucial aspect of neural growth is determining the optimal growth timing.…

Machine Learning · Computer Science 2024-01-09 Haihang Wu , Wei Wang , Tamasha Malepathirana , Damith Senanayake , Denny Oetomo , Saman Halgamuge

Artificial neural networks (ANNs) have very successfully been used in numerical simulations for a series of computational problems ranging from image classification/image recognition, speech recognition, time series analysis, game…

Numerical Analysis · Mathematics 2023-08-02 Philipp Grohs , Fabian Hornung , Arnulf Jentzen , Philippe von Wurstemberger

We study differentially private (DP) stochastic optimization (SO) with loss functions whose worst-case Lipschitz parameter over all data may be extremely large or infinite. To date, the vast majority of work on DP SO assumes that the loss…

Machine Learning · Computer Science 2024-10-01 Andrew Lowy , Meisam Razaviyayn

Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis of closed-loop systems with reinforcement learning…

Machine Learning · Computer Science 2023-01-18 Mahyar Fazlyab , Alexander Robey , Hamed Hassani , Manfred Morari , George J. Pappas

We consider a stochastic version of the proximal point algorithm for optimization problems posed on a Hilbert space. A typical application of this is supervised learning. While the method is not new, it has not been extensively analyzed in…

Optimization and Control · Mathematics 2021-09-28 Monika Eisenmann , Tony Stillfjord , Måns Williamson

Classical assumptions like strong convexity and Lipschitz smoothness often fail to capture the nature of deep learning optimization problems, which are typically non-convex and non-smooth, making traditional analyses less applicable. This…

Machine Learning · Computer Science 2025-05-01 Binchuan Qi , Wei Gong , Li Li

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a $k$ hidden node shallow network with quadratic activation and $n$ training data points, we show as long as $ k \ge \sqrt{2n}$,…

Machine Learning · Computer Science 2018-06-18 Simon S. Du , Jason D. Lee

Beside the minimization of the prediction error, two of the most desirable properties of a regression scheme are stability and interpretability. Driven by these principles, we propose continuous-domain formulations for one-dimensional…

Machine Learning · Computer Science 2021-12-28 Shayan Aziznejad , Thomas Debarre , Michael Unser

We provide a theoretical explanation for the effectiveness of gradient clipping in training deep neural networks. The key ingredient is a new smoothness condition derived from practical neural network training examples. We observe that…

Optimization and Control · Mathematics 2020-02-12 Jingzhao Zhang , Tianxing He , Suvrit Sra , Ali Jadbabaie

There is an increasing body of evidence suggesting that exact nearest neighbour search in high-dimensional spaces is affected by the curse of dimensionality at a fundamental level. Does it necessarily mean that the same is true for k…

Machine Learning · Statistics 2021-02-18 Vladimir Pestov

State-of-the-art approaches for training Differentially Private (DP) Deep Neural Networks (DNN) face difficulties to estimate tight bounds on the sensitivity of the network's layers, and instead rely on a process of per-sample gradient…

Despite the success of Lipschitz regularization in stabilizing GAN training, the exact reason of its effectiveness remains poorly understood. The direct effect of $K$-Lipschitz regularization is to restrict the $L2$-norm of the neural…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Yipeng Qin , Niloy Mitra , Peter Wonka