English
Related papers

Related papers: Training Neural Networks is NP-Hard in Fixed Dimen…

200 papers

A resolving set $S$ of a graph $G$ is a subset of its vertices such that no two vertices of $G$ have the same distance vector to $S$. The Metric Dimension problem asks for a resolving set of minimum size, and in its decision form, a…

Computational Complexity · Computer Science 2019-07-19 Édouard Bonnet , Nidhi Purohit

In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Currently, insightful theories still rely on assumptions…

Machine Learning · Computer Science 2025-04-01 Devon Jarvis , Richard Klein , Benjamin Rosman , Andrew M. Saxe

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 study the parameter complexity of robust memorization for $\mathrm{ReLU}$ networks: the number of parameters required to interpolate any given dataset with $\epsilon$-separation between differently labeled points, while ensuring…

Machine Learning · Computer Science 2025-10-29 Yujun Kim , Chaewon Moon , Chulhee Yun

Understanding the relationship between the depth of a neural network and its representational capacity is a central problem in deep learning theory. In this work, we develop a geometric framework to analyze the expressivity of ReLU networks…

Machine Learning · Computer Science 2026-03-20 Juan L. Valerdi

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical points (where the…

Machine Learning · Computer Science 2024-10-15 Adrian Barbu

Benign overfitting refers to how over-parameterized neural networks can fit training data perfectly and generalize well to unseen data. While this has been widely investigated theoretically, existing works are limited to two-layer networks…

Machine Learning · Computer Science 2024-10-28 Shuning Shang , Xuran Meng , Yuan Cao , Difan Zou

The number of linear regions is one of the distinct properties of the neural networks using piecewise linear activation functions such as ReLU, comparing with those conventional ones using other activation functions. Previous studies showed…

Machine Learning · Computer Science 2020-07-15 Rui Zhu , Bo Lin , Haixu Tang

Previous works proved that the combination of the linear neuron network with nonlinear activation functions (e.g. ReLu) can achieve nonlinear function approximation. However, simply widening or deepening the network structure will introduce…

Networking and Internet Architecture · Computer Science 2020-11-24 Zirui Xu , Jinjun Xiong , Fuxun Yu , Xiang Chen

Linear layers in neural networks (NNs) trained by gradient descent can be expressed as a key-value memory system which stores all training datapoints and the initial weights, and produces outputs using unnormalised dot attention over the…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Róbert Csordás , Jürgen Schmidhuber

We present empirical evidence that neural networks with ReLU and Absolute Value activations learn distance-based representations. We independently manipulate both distance and intensity properties of internal activations in trained models,…

Machine Learning · Computer Science 2024-11-28 Alan Oursland

We demonstrate that deep neural networks with the ReLU activation function can efficiently approximate the solutions of various types of parametric linear transport equations. For non-smooth initial conditions, the solutions of these PDEs…

Numerical Analysis · Mathematics 2020-01-31 Fabian Laakmann , Philipp Petersen

We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent…

Numerical Analysis · Mathematics 2020-05-15 Gitta Kutyniok , Philipp Petersen , Mones Raslan , Reinhold Schneider

Neural networks with the Rectified Linear Unit (ReLU) nonlinearity are described by a vector of parameters $\theta$, and realized as a piecewise linear continuous function $R_{\theta}: x \in \mathbb R^{d} \mapsto R_{\theta}(x) \in \mathbb…

Machine Learning · Computer Science 2022-06-08 Pierre Stock , Rémi Gribonval

Recently, theoretical analyses of deep neural networks have broadly focused on two directions: 1) Providing insight into neural network training by SGD in the limit of infinite hidden-layer width and infinitesimally small learning rate…

Machine Learning · Computer Science 2023-09-27 Rajat Vadiraj Dwaraknath , Tolga Ergen , Mert Pilanci

The success of deep learning in the computer vision and natural language processing communities can be attributed to training of very deep neural networks with millions or billions of parameters which can then be trained with massive…

Machine Learning · Computer Science 2021-02-17 Kei Ota , Devesh K. Jha , Asako Kanezaki

The choice of architecture of a neural network influences which functions will be realizable by that neural network and, as a result, studying the expressiveness of a chosen architecture has received much attention. In ReLU neural networks,…

Machine Learning · Computer Science 2024-12-18 Natalie Brownlowe , Christopher R. Cornwell , Ethan Montes , Gabriel Quijano , Grace Stulman , Na Zhang

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

Machine Learning · Computer Science 2024-10-08 Arthur Jacot , Peter Súkeník , Zihan Wang , Marco Mondelli

This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with well-separated input vectors: Any pair of input data with the…

Machine Learning · Computer Science 2024-03-26 Hancheng Min , Enrique Mallada , René Vidal

Deep learning, in the form of artificial neural networks, has achieved remarkable practical success in recent years, for a variety of difficult machine learning applications. However, a theoretical explanation for this remains a major open…

Machine Learning · Computer Science 2016-06-15 Itay Safran , Ohad Shamir
‹ Prev 1 8 9 10 Next ›