English
Related papers

Related papers: Principled Simplicial Neural Networks for Trajecto…

200 papers

Simplicial complexes are extensively studied in the field of algebraic topology. They have gained attention in recent time due to their applications in fields like theoretical distributed computing and simplicial neural networks. Graphs are…

Discrete Mathematics · Computer Science 2025-12-16 Sukrit Chakraborty , Prasanta Choudhury , Arindam Mukherjee

The ability to learn and predict simple functions is a key aspect of human intelligence. Recent works have started to explore this ability using transformer architectures, however it remains unclear whether this is sufficient to…

Machine Learning · Computer Science 2023-04-21 Simon Segert , Jonathan Cohen

Simplicial complexes are a popular tool used to model higher-order interactions between elements of complex social and biological systems. In this paper, we study some combinatorial aspects of a class of simplicial complexes created by a…

Combinatorics · Mathematics 2023-05-17 Zixuan Xie , Yucheng Wang , Wanyue Xu , Liwang Zhu , Wei Li , Zhongzhi Zhang

Exploiting symmetries and invariance in data is a powerful, yet not fully exploited, way to achieve better generalisation with more efficiency. In this paper, we introduce two graph network architectures that are equivariant to several…

Machine Learning · Computer Science 2021-06-01 Francesco Farina , Emma Slade

This paper introduces a model that identifies spatial relationships for a structural analysis based on the concept of simplicial complex. The spatial relationships are identified through overlapping two map layers, namely a primary layer…

Data Analysis, Statistics and Probability · Physics 2008-01-15 Bin Jiang , Itzhak Omer

Arguments inspired by algorithmic information theory predict an inverse relation between the probability and complexity of output patterns in a wide range of input-output maps. This phenomenon is known as \emph{simplicity bias}. By viewing…

Dynamical Systems · Mathematics 2024-05-14 Kamaludin Dingle , Mohammad Alaskandarani , Boumediene Hamzi , Ard A. Louis

In this paper we introduce a new model of random simplicial complexes depending on multiple probability parameters. This model includes the well-known Linial - Meshulam random simplicial complexes and random clique complexes as special…

Algebraic Topology · Mathematics 2015-03-03 A. Costa , M. Farber

Neural networks trained with gradient-based methods exhibit a strong simplicity bias: they learn simpler statistical features of their data before moving to more complex features. Previous analyses of this phenomenon have largely focused on…

Machine Learning · Statistics 2026-05-19 Fabiola Ricci , Claudia Merger , Sebastian Goldt

Simplicial complexes are higher-order combinatorial structures which have been used to represent real-world complex systems. In this paper, we concentrate on the local patterns in simplicial complexes called simplets, a generalization of…

Social and Information Networks · Computer Science 2023-04-26 Hyunju Kim , Jihoon Ko , Fanchen Bu , Kijung Shin

It is increasingly common for data to possess intricate structure, necessitating new models and analytical tools. Graphs, a prominent type of structure, can encode the relationships between any two entities (nodes). However, graphs neither…

Signal Processing · Electrical Eng. & Systems 2026-02-04 Madeline Navarro , Andrei Buciulea , Santiago Segarra , Antonio Marques

We develop an algorithm for systematic design of a large artificial neural network using a progression property. We find that some non-linear functions, such as the rectifier linear unit and its derivatives, hold the property. The…

Neural and Evolutionary Computing · Computer Science 2017-10-24 Saikat Chatterjee , Alireza M. Javid , Mostafa Sadeghi , Partha P. Mitra , Mikael Skoglund

Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a…

Machine Learning · Computer Science 2023-05-31 Emmanouil Theodosis , Karim Helwani , Demba Ba

Prediction accuracy and model explainability are the two most important objectives when developing machine learning algorithms to solve real-world problems. The neural networks are known to possess good prediction performance, but lack of…

Machine Learning · Statistics 2019-09-04 Zebin Yang , Aijun Zhang , Agus Sudjianto

Our work is concerned with simplicial complexes that describe higher-order interactions in real complex systems. This description allows to go beyond the pairwise node-to-node representation that simple networks provide and to capture a…

Statistical Mechanics · Physics 2025-11-13 Sara Najem , Dima Mrad , Mohammad Elsayed

We present a new manifold learning algorithm that takes a set of data points lying on or near a lower dimensional manifold as input, possibly with noise, and outputs a simplicial complex that fits the data and the manifold. We have…

Numerical Analysis · Mathematics 2012-09-17 Thomas Hunt , Arthur J. Krener

We present a structured neural network architecture that is inspired by linear time-varying dynamical systems. The network is designed to mimic the properties of linear dynamical systems which makes analysis and control simple. The…

Robotics · Computer Science 2018-08-06 Alexander Broad , Ian Abraham , Todd Murphey , Brenna Argall

Real-world networks such as the Internet and WWW have many common traits. Until now, hundreds of models were proposed to characterize these traits for understanding the networks. Because different models used very different mechanisms, it…

Social and Information Networks · Computer Science 2014-09-02 Bojin Zheng , Hongrun Wu , Li Kuang , Jun Qin , Wenhua Du , Jianmin Wang , Deyi Li

Neural networks typically exhibit permutation symmetries which contribute to the non-convexity of the networks' loss landscapes, since linearly interpolating between two permuted versions of a trained network tends to encounter a high loss…

Machine Learning · Computer Science 2024-04-10 Ekansh Sharma , Devin Kwok , Tom Denton , Daniel M. Roy , David Rolnick , Gintare Karolina Dziugaite

A simple and accurate relationship is demonstrated that links the average shortest path, nodes, and edges in a complex network. This relationship takes advantage of the concept of link density and shows a large improvement in fitting…

Physics and Society · Physics 2013-04-24 Reginald D. Smith

Traditionally, most complex intelligence architectures are extremely non-convex, which could not be well performed by convex optimization. However, this paper decomposes complex structures into three types of nodes: operators, algorithms…

Machine Learning · Computer Science 2018-01-16 Han Xiao