English
Related papers

Related papers: Neural Polytopes

200 papers

In many contexts, simpler models are preferable to more complex models and the control of this model complexity is the goal for many methods in machine learning such as regularization, hyperparameter tuning and architecture design. In deep…

Machine Learning · Computer Science 2022-12-27 Benoit Dherin , Michael Munn , Mihaela Rosca , David G. T. Barrett

We introduce a class of algebraic varieties naturally associated with ReLU neural networks, arising from the piecewise linear structure of their outputs across activation regions in input space, and the piecewise multilinear structure in…

Algebraic Geometry · Mathematics 2025-08-07 Yulia Alexandr , Guido Montúfar

An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been…

Machine Learning · Computer Science 2019-12-30 Fayyaz ul Amir Afsar Minhas , Amina Asif

Deep neural networks can approximate functions on different types of data, from images to graphs, with varied underlying structure. This underlying structure can be viewed as the geometry of the data manifold. By extending recent advances…

Machine Learning · Computer Science 2023-01-03 Saket Tiwari , George Konidaris

The information processing abilities of a multilayer neural network with a number of hidden units scaling as the input dimension are studied using statistical mechanics methods. The mapping from the input layer to the hidden units is…

Statistical Mechanics · Physics 2009-11-07 Michal Rosen-Zvi , Andreas Engel , Ido Kanter

We develop a novel theoretical framework for analyzing ReLU neural networks through the lens of a combinatorial object we term the ReLU Transition Graph (RTG). In this graph, each node corresponds to a linear region induced by the network's…

Machine Learning · Computer Science 2025-05-30 Sahil Rajesh Dhayalkar

Neural networks activated by the rectified linear unit (ReLU) play a central role in the recent development of deep learning. The topic of approximating functions from H\"older spaces by these networks is crucial for understanding the…

Machine Learning · Computer Science 2023-07-25 Tong Mao , Ding-Xuan Zhou

Neural networks with a large number of parameters often do not overfit, owing to implicit regularization that favors \lq good\rq{} networks. Other related and puzzling phenomena include properties of flat minima, saddle-to-saddle dynamics,…

Artificial Intelligence · Computer Science 2026-01-06 Joachim Bona-Pellissier , François Malgouyres , François Bachoc

We discuss approximation of functions using deep neural nets. Given a function $f$ on a $d$-dimensional manifold $\Gamma \subset \mathbb{R}^m$, we construct a sparsely-connected depth-4 neural network and bound its error in approximating…

Machine Learning · Statistics 2017-04-24 Uri Shaham , Alexander Cloninger , Ronald R. Coifman

We study the expressivity of sparse maxout networks, where each neuron takes a fixed number of inputs from the previous layer and employs a, possibly multi-argument, maxout activation. This setting captures key characteristics of…

Machine Learning · Computer Science 2025-10-17 Moritz Grillo , Tobias Hofmann

We develop a framework for analyzing parameter symmetries in deep ReLU networks and obtain a complete characterization of the generic parameter fibers for three-layer bottleneck architectures. Our approach provides explicit semi-algebraic…

Machine Learning · Computer Science 2026-05-19 Johanna Marie Gegenfurtner , Moritz Grillo , Guido Montúfar

We study ReLU deep neural networks (DNNs) by investigating their connections with the hierarchical basis method in finite element methods. First, we show that the approximation schemes of ReLU DNNs for $x^2$ and $xy$ are composition…

Numerical Analysis · Mathematics 2022-08-09 Juncai He , Lin Li , Jinchao Xu

In this paper, we consider one dimensional (shallow) ReLU neural networks in which weights are chosen randomly and only the terminal layer is trained. First, we mathematically show that for such networks L2-regularized regression…

Machine Learning · Computer Science 2023-10-05 Jakob Heiss , Josef Teichmann , Hanna Wutte

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

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions…

Machine Learning · Computer Science 2022-09-07 Qingguo Hong , Jonathan W. Siegel , Qinyang Tan , Jinchao Xu

The universal approximation property uniformly with respect to weakly compact families of measures is established for several classes of neural networks. To that end, we prove that these neural networks are dense in Orlicz spaces, thereby…

Machine Learning · Statistics 2025-10-13 Mihriban Ceylan , David J. Prömel

We train deep generative models on datasets of reflexive polytopes. This enables us to compare how well the models have picked up on various global properties of generated samples. Our datasets are complete in the sense that every single…

Machine Learning · Computer Science 2021-05-31 Bernt Ivar Utstøl Nødland

Universal approximation theorem suggests that a shallow neural network can approximate any function. The input to neurons at each layer is a weighted sum of previous layer neurons and then an activation is applied. These activation…

Machine Learning · Computer Science 2020-10-30 Bhaavan Goel

We study convolutional neural networks with monomial activation functions. Specifically, we prove that their parameterization map is regular and is an isomorphism almost everywhere, up to rescaling the filters. By leveraging on tools from…

Machine Learning · Computer Science 2025-03-04 Vahid Shahverdi , Giovanni Luca Marchetti , Kathlén Kohn

We define the local complexity of a neural network with continuous piecewise linear activations as a measure of the density of linear regions over an input data distribution. We show theoretically that ReLU networks that learn…

Machine Learning · Computer Science 2025-07-15 Niket Patel , Guido Montufar