English
Related papers

Related papers: Understanding Two-Layer Neural Networks with Smoot…

200 papers

The training of two-layer neural networks with nonlinear activation functions is an important non-convex optimization problem with numerous applications and promising performance in layerwise deep learning. In this paper, we develop exact…

Machine Learning · Computer Science 2021-01-11 Burak Bartan , Mert Pilanci

In this paper, we study neural networks from the point of view of nonsmooth optimisation, namely, quasidifferential calculus. We restrict ourselves to the case of uniform approximation by a neural network without hidden layers, the…

Optimization and Control · Mathematics 2025-03-05 Vinesha Peiris , Nadezda Sukhorukova

Deep neural networks, as a powerful system to represent high dimensional complex functions, play a key role in deep learning. Convergence of deep neural networks is a fundamental issue in building the mathematical foundation for deep…

Machine Learning · Computer Science 2022-10-04 Wentao Huang , Yuesheng Xu , Haizhang Zhang

Recent findings suggest that consecutive layers of neural networks with the ReLU activation function \emph{fold} the input space during the learning process. While many works hint at this phenomenon, an approach to quantify the folding was…

Machine Learning · Computer Science 2025-03-12 Michal Lewandowski , Bernhard Heinzl , Raphael Pisoni , Bernhard A. Moser

The implicit bias towards solutions with favorable properties is believed to be a key reason why neural networks trained by gradient-based optimization can generalize well. While the implicit bias of gradient flow has been widely studied…

Machine Learning · Computer Science 2023-10-31 Yiwen Kou , Zixiang Chen , Quanquan Gu

The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of…

Computer Vision and Pattern Recognition · Computer Science 2019-10-15 Avanti Shrikumar , Peyton Greenside , Anshul Kundaje

We prove that finding all globally optimal two-layer ReLU neural networks can be performed by solving a convex optimization program with cone constraints. Our analysis is novel, characterizes all optimal solutions, and does not leverage…

Machine Learning · Computer Science 2022-03-15 Yifei Wang , Jonathan Lacotte , Mert Pilanci

Neural networks trained to minimize the logistic (a.k.a. cross-entropy) loss with gradient-based methods are observed to perform well in many supervised classification tasks. Towards understanding this phenomenon, we analyze the training…

Optimization and Control · Mathematics 2020-06-23 Lenaic Chizat , Francis Bach

We prove some new results concerning the approximation rate of neural networks with general activation functions. Our first result concerns the rate of approximation of a two layer neural network with a polynomially-decaying non-sigmoidal…

Classical Analysis and ODEs · Mathematics 2021-01-05 Jonathan W. Siegel , Jinchao Xu

The Forward-Forward algorithm is an alternative learning method which consists of two forward passes rather than a forward and backward pass employed by backpropagation. Forward-Forward networks employ layer local loss functions which are…

Machine Learning · Computer Science 2025-04-16 Reece Adamson

Neural networks can implement arbitrary functions. But, mechanistically, what are the tools at their disposal to construct the target? For classification tasks, the network must transform the data classes into a linearly separable…

Machine Learning · Computer Science 2022-03-23 Christian Keup , Moritz Helias

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

Even when neural networks are widely used in a large number of applications, they are still considered as black boxes and present some difficulties for dimensioning or evaluating their prediction error. This has led to an increasing…

Machine Learning · Statistics 2021-05-11 Pablo Morala , Jenny Alexandra Cifuentes , Rosa E. Lillo , Iñaki Ucar

Giving provable guarantees for learning neural networks is a core challenge of machine learning theory. Most prior work gives parameter recovery guarantees for one hidden layer networks, however, the networks used in practice have multiple…

Machine Learning · Computer Science 2020-02-21 Surbhi Goel , Rina Panigrahy

This paper provides a theoretical framework on the solution of feedforward ReLU networks for interpolations, in terms of what is called an interpolation matrix, which is the summary, extension and generalization of our three preceding…

Machine Learning · Computer Science 2022-12-13 Changcun Huang

The success of Neural networks in providing miraculous results when applied to a wide variety of tasks is astonishing. Insight in the working can be obtained by studying the universal approximation property of neural networks. It is proved…

Machine Learning · Computer Science 2021-11-17 R Subhash Chandra Bose , Kakarla Yaswanth

We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem. Our approach is based on representing a non-decreasing activation function…

Machine Learning · Computer Science 2018-06-22 Armin Askari , Geoffrey Negiar , Rajiv Sambharya , Laurent El Ghaoui

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the…

Machine Learning · Statistics 2019-05-01 Gang Wang , Georgios B. Giannakis , Jie Chen

We present SiLU network constructions whose approximation efficiency depends critically on proper hyperparameter tuning. For the square function $x^2$, with optimally chosen shift $a$ and scale $\beta$, we achieve approximation error…

Machine Learning · Computer Science 2026-02-24 Koffi O. Ayena

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu
‹ Prev 1 4 5 6 7 8 10 Next ›