English
Related papers

Related papers: Curse of Dimensionality in Neural Network Optimiza…

200 papers

This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparameterized two-layer neural networks. In particular, we consider the minimax optimization problem stemming from estimating linear…

Machine Learning · Computer Science 2024-10-25 Yuchen Zhu , Yufeng Zhang , Zhaoran Wang , Zhuoran Yang , Xiaohong Chen

We prove the curse of dimensionality in the worst case setting for multivariate numerical integration for various classes of smooth functions. We prove the results when the domains are isotropic convex bodies with small diameter satisfying…

Numerical Analysis · Mathematics 2019-08-15 Aicke Hinrichs , Joscha Prochno , Mario Ullrich

Plasticity, the ability of a neural network to quickly change its predictions in response to new information, is essential for the adaptability and robustness of deep reinforcement learning systems. Deep neural networks are known to lose…

Machine Learning · Computer Science 2023-11-28 Clare Lyle , Zeyu Zheng , Evgenii Nikishin , Bernardo Avila Pires , Razvan Pascanu , Will Dabney

We study the high-dimensional training dynamics of a shallow neural network with quadratic activation in a teacher-student setup. We focus on the extensive-width regime, where the teacher and student network widths scale proportionally with…

Optimization and Control · Mathematics 2026-01-16 Simon Martin , Giulio Biroli , Francis Bach

Randomized Smoothing (RS) has been proven a promising method for endowing an arbitrary image classifier with certified robustness. However, the substantial uncertainty inherent in the high-dimensional isotropic Gaussian noise imposes the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Song Xia , Yi Yu , Xudong Jiang , Henghui Ding

As annotations of data can be scarce in large-scale practical problems, leveraging unlabelled examples is one of the most important aspects of machine learning. This is the aim of semi-supervised learning. To benefit from the access to…

Machine Learning · Statistics 2021-11-30 Vivien Cabannes , Loucas Pillaud-Vivien , Francis Bach , Alessandro Rudi

Policy gradient methods equipped with deep neural networks have achieved great success in solving high-dimensional reinforcement learning (RL) problems. However, current analyses cannot explain why they are resistant to the curse of…

Machine Learning · Computer Science 2024-01-17 Zhenghao Xu , Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the weights of the neural network. But beyond the weights, the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Minjing Dong , Yanxi Li , Yunhe Wang , Chang Xu

Learning operators between infinitely dimensional spaces is an important learning task arising in wide applications in machine learning, imaging science, mathematical modeling and simulations, etc. This paper studies the nonparametric…

Machine Learning · Statistics 2022-01-04 Hao Liu , Haizhao Yang , Minshuo Chen , Tuo Zhao , Wenjing Liao

Threshold activation functions are highly preferable in neural networks due to their efficiency in hardware implementations. Moreover, their mode of operation is more interpretable and resembles that of biological neurons. However,…

Machine Learning · Computer Science 2023-03-07 Tolga Ergen , Halil Ibrahim Gulluk , Jonathan Lacotte , Mert Pilanci

Deriving sharp and computable upper bounds of the Lipschitz constant of deep neural networks is crucial to formally guarantee the robustness of neural-network based models. We analyse three existing upper bounds written for the $l^2$ norm.…

Machine Learning · Computer Science 2024-10-29 Moreno Pintore , Bruno Després

We demonstrate two new important properties of the 1-path-norm of shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal operator which can be efficiently computed, allowing the use of…

Machine Learning · Computer Science 2020-07-16 Fabian Latorre , Paul Rolland , Nadav Hallak , Volkan Cevher

We study unconstrained Online Linear Optimization with Lipschitz losses. Motivated by the pursuit of instance optimality, we propose a new algorithm that simultaneously achieves ($i$) the AdaGrad-style second order gradient adaptivity; and…

Machine Learning · Computer Science 2024-02-23 Zhiyu Zhang , Heng Yang , Ashok Cutkosky , Ioannis Ch. Paschalidis

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the over-parametrized regime where the layer width $m$ is larger than the input dimension $d$.…

Machine Learning · Computer Science 2021-03-22 Stefano Sarao Mannelli , Eric Vanden-Eijnden , Lenka Zdeborová

Training neural networks involves solving large-scale non-convex optimization problems. This task has long been believed to be extremely difficult, with fear of local minima and other obstacles motivating a variety of schemes to improve…

Neural and Evolutionary Computing · Computer Science 2015-05-25 Ian J. Goodfellow , Oriol Vinyals , Andrew M. Saxe

In binary classification and regression problems, it is well understood that Lipschitz continuity and smoothness of the loss function play key roles in governing generalization error bounds for empirical risk minimization algorithms. In…

Machine Learning · Computer Science 2016-09-14 Ambuj Tewari , Sougata Chaudhuri

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

In data-driven optimization, sample average approximation (SAA) is known to suffer from the so-called optimizer's curse that causes an over-optimistic evaluation of the solution performance. We argue that a special type of distributionallly…

Optimization and Control · Mathematics 2023-10-13 Zhenyuan Liu , Bart P. G. Van Parys , Henry Lam

Finding the optimal size of deep learning models is very actual and of broad impact, especially in energy-saving schemes. Very recently, an unexpected phenomenon, the ``double descent'', has caught the attention of the deep learning…

Machine Learning · Computer Science 2023-12-27 Victor Quétu , Enzo Tartaglione