English
Related papers

Related papers: Capacity Bounds for Hyperbolic Neural Network Repr…

200 papers

Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to better capture the hierarchical nature of data. In this…

Machine Learning · Computer Science 2021-03-18 Ryohei Shimizu , Yusuke Mukuta , Tatsuya Harada

We contribute towards resolving the open question of how many hidden layers are required in ReLU networks for exactly representing all continuous and piecewise linear functions on $\mathbb{R}^d$. While the question has been resolved in…

Machine Learning · Computer Science 2025-10-24 Moritz Grillo , Christoph Hertrich , Georg Loho

The recent successes and spread of large neural language models (LMs) call for a thorough understanding of their computational ability. Describing their computational abilities through LMs' \emph{representational capacity} is a lively area…

Computation and Language · Computer Science 2024-06-19 Anej Svete , Franz Nowak , Anisha Mohamed Sahabdeen , Ryan Cotterell

Hyperbolic neural networks have emerged as a powerful tool for modeling hierarchical data structures prevalent in real-world datasets. Notably, residual connections, which facilitate the direct flow of information across layers, have been…

Machine Learning · Computer Science 2025-01-14 Neil He , Menglin Yang , Rex Ying

The purpose of the present paper is to study the computation complexity of deep ReLU neural networks to approximate functions in H\"older-Nikol'skii spaces of mixed smoothness $H_\infty^\alpha(\mathbb{I}^d)$ on the unit cube…

Numerical Analysis · Mathematics 2021-03-02 Dinh Dũng , Van Kien Nguyen , Mai Xuan Thao

We study the size of a neural network needed to approximate the maximum function over $d$ inputs, in the most basic setting of approximating with respect to the $L_2$ norm, for continuous distributions, for a network that uses ReLU…

Machine Learning · Computer Science 2023-11-08 Itay Safran , Daniel Reichman , Paul Valiant

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

While deep neural networks (DNNs) have become a standard architecture for many machine learning tasks, their internal decision-making process and general interpretability is still poorly understood. Conversely, common decision trees are…

Machine Learning · Computer Science 2022-02-02 Coenraad Mouton , Marelie H. Davel

Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic Neural Networks (HNNs) exploit such representational power by lifting Euclidean features into hyperbolic space for classification, outperforming Euclidean…

Machine Learning · Computer Science 2022-05-17 Yunhui Guo , Xudong Wang , Yubei Chen , Stella X. Yu

We shed light on a pitfall and an opportunity in physics-informed neural networks (PINNs). We prove that a multilayer perceptron (MLP) only with ReLU (Rectified Linear Unit) or ReLU-like Lipschitz activation functions will always lead to a…

Computational Physics · Physics 2023-04-04 Kuangdai Leng , Jeyan Thiyagalingam

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

In 1988, Eric B. Baum showed that two-layers neural networks with threshold activation function can perfectly memorize the binary labels of $n$ points in general position in $\mathbb{R}^d$ using only $\ulcorner n/d \urcorner$ neurons. We…

Machine Learning · Computer Science 2020-11-04 Sébastien Bubeck , Ronen Eldan , Yin Tat Lee , Dan Mikulincer

We develop a statistical mechanical approach based on the replica method to study the design space of deep and wide neural networks constrained to meet a large number of training data. Specifically, we analyze the configuration space of the…

Disordered Systems and Neural Networks · Physics 2020-04-17 Hajime Yoshino

We consider the problem of exact computation of the maximum function over $d$ real inputs using ReLU neural networks. We prove a depth hierarchy, wherein width $\Omega\big(d^{1+\frac{1}{2^{k-2}-1}}\big)$ is necessary to represent the…

Machine Learning · Computer Science 2026-01-06 Itay Safran

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure. A few recent approaches have successfully demonstrated the benefits of…

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

Numerical Analysis · Mathematics 2020-11-02 Austin R. Benson , Anil Damle , Alex Townsend

Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks. The…

Machine Learning · Statistics 2018-09-20 Benjamin Paul Chamberlain , James Clough , Marc Peter Deisenroth

Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we…

Machine Learning · Computer Science 2019-10-30 Qi Liu , Maximilian Nickel , Douwe Kiela

We study two models of ReLU neural networks: monotone networks (ReLU$^+$) and input convex neural networks (ICNN). Our focus is on expressivity, mostly in terms of depth, and we prove the following lower bounds. For the maximum function…

Machine Learning · Computer Science 2025-05-12 Egor Bakaev , Florestan Brunck , Christoph Hertrich , Daniel Reichman , Amir Yehudayoff

The impressive expressive power of deep neural networks (DNNs) underlies their widespread applicability. However, while the theoretical capacity of deep architectures is high, the practical expressive power achieved through successful…

Machine Learning · Computer Science 2023-12-21 Zezhong Zhang , Feng Bao , Guannan Zhang