English
Related papers

Related papers: A Scale Invariant Flatness Measure for Deep Networ…

200 papers

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Machine Learning · Computer Science 2024-03-01 Zhen Qin , Xuwei Tan , Zhihui Zhu

This paper proves an abstract theorem addressing in a unified manner two important problems in function approximation: avoiding curse of dimensionality and estimating the degree of approximation for out-of-sample extension in manifold…

Machine Learning · Computer Science 2019-11-05 Hrushikesh N. Mhaskar

The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balancing the variance among weights per layer to maintain…

Machine Learning · Computer Science 2020-06-05 Maciej Skorski , Alessandro Temperoni , Martin Theobald

We study the properties of common loss surfaces through their Hessian matrix. In particular, in the context of deep learning, we empirically show that the spectrum of the Hessian is composed of two parts: (1) the bulk centered near zero,…

Machine Learning · Computer Science 2018-05-08 Levent Sagun , Utku Evci , V. Ugur Guney , Yann Dauphin , Leon Bottou

We study the properties of alignment, a form of implicit regularization, in linear neural networks under gradient descent. We define alignment for fully connected networks with multidimensional outputs and show that it is a natural…

Machine Learning · Computer Science 2020-06-18 Adityanarayanan Radhakrishnan , Eshaan Nichani , Daniel Bernstein , Caroline Uhler

The stochastic gradient descent (SGD) method is most widely used for deep neural network (DNN) training. However, the method does not always converge to a flat minimum of the loss surface that can demonstrate high generalization capability.…

Machine Learning · Computer Science 2020-09-08 Wonyong Sung , Iksoo Choi , Jinhwan Park , Seokhyun Choi , Sungho Shin

Recent experiments have shown that, often, when training a neural network with gradient descent (GD) with a step size $\eta$, the operator norm of the Hessian of the loss grows until it approximately reaches $2/\eta$, after which it…

Machine Learning · Computer Science 2024-06-07 Philip M. Long , Peter L. Bartlett

Overparameterized shallow neural networks admit substantial parameter redundancy: distinct parameter vectors may represent the same predictor due to hidden-unit permutations, rescalings, and related symmetries. As a result, geometric…

Machine Learning · Computer Science 2026-03-24 Hang-Cheng Dong , Pengcheng Cheng

Gradient descent on overparameterized neural networks typically operates at the Edge of Stability (EoS), where the largest Hessian eigenvalue hovers around a step-size-dependent threshold. We study how sparse connectivity changes…

Machine Learning · Statistics 2026-05-08 Tongtong Liang , Esha Singh , Rahul Parhi , Alexander Cloninger , Yu-Xiang Wang

Real world data often exhibit low-dimensional geometric structures, and can be viewed as samples near a low-dimensional manifold. This paper studies nonparametric regression of H\"{o}lder functions on low-dimensional manifolds using deep…

Machine Learning · Computer Science 2022-02-24 Minshuo Chen , Haoming Jiang , Wenjing Liao , Tuo Zhao

In this paper we approach the problem of unique and stable identifiability of generic deep artificial neural networks with pyramidal shape and smooth activation functions from a finite number of input-output samples. More specifically we…

Machine Learning · Computer Science 2021-01-19 Christian Fiedler , Massimo Fornasier , Timo Klock , Michael Rauchensteiner

Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Greg Yang

We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that infinite-depth ResNets behave as if they were infinitely wide, regardless of their actual width. More…

Machine Learning · Computer Science 2026-03-04 Lénaïc Chizat

Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the…

Optimization and Control · Mathematics 2020-11-04 Lenaic Chizat

Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling factors. We introduce an automated scaling approach…

Machine Learning · Computer Science 2024-02-21 Akash Guna R. T , Arnav Chavan , Deepak Gupta

In this paper, we prove that depth with nonlinearity creates no bad local minima in a type of arbitrarily deep ResNets with arbitrary nonlinear activation functions, in the sense that the values of all local minima are no worse than the…

Machine Learning · Statistics 2019-07-10 Kenji Kawaguchi , Yoshua Bengio

Understanding the operation of biological and artificial networks remains a difficult and important challenge. To identify general principles, researchers are increasingly interested in surveying large collections of networks that are…

Machine Learning · Statistics 2022-01-14 Alex H. Williams , Erin Kunz , Simon Kornblith , Scott W. Linderman

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large…

Machine Learning · Computer Science 2025-10-21 Lachlan Ewen MacDonald , Hancheng Min , Leandro Palma , Salma Tarmoun , Ziqing Xu , René Vidal

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

Deep neural networks (DNNs) are so over-parametrized that recent research has found them to already contain a subnetwork with high accuracy at their randomly initialized state. Finding these subnetworks is a viable alternative training…

Computer Vision and Pattern Recognition · Computer Science 2021-11-25 Ángel López García-Arias , Masanori Hashimoto , Masato Motomura , Jaehoon Yu
‹ Prev 1 8 9 10 Next ›