English
Related papers

Related papers: Learning to be Simple

200 papers

It is shown that the classification theorems for semisimple algebraic groups in characteristic zero can be derived quite simply and naturally from the corresponding theorems for Lie algebras by using a little of the theory of tensor…

Representation Theory · Mathematics 2007-05-23 J. S. Milne

Learning controllable and generalizable representation of multivariate data with desired structural properties remains a fundamental problem in machine learning. In this paper, we present a novel framework for learning generative models…

Machine Learning · Computer Science 2020-10-05 Ruixiang Zhang , Masanori Koyama , Katsuhiko Ishiguro

Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…

Machine Learning · Statistics 2017-02-28 Shakir Mohamed , Balaji Lakshminarayanan

We show how to efficiently count and generate uniformly at random finitely generated subgroups of the modular group $\textsf{PSL}(2,\mathbb{Z})$ of a given isomorphism type. The method to achieve these results relies on a natural map of…

Group Theory · Mathematics 2024-12-10 Frédérique Bassino , Cyril Nicaud , Pascal Weil

An important characteristic of neural networks is their ability to learn representations of the input data with effective features for prediction, which is believed to be a key factor to their superior empirical performance. To better…

Machine Learning · Computer Science 2022-06-06 Zhenmei Shi , Junyi Wei , Yingyu Liang

Safety critical systems strongly require the quality aspects of artificial intelligence including explainability. In this paper, we analyzed a trained network to extract features which mainly contribute the inference. Based on the analysis,…

Computer Vision and Pattern Recognition · Computer Science 2017-12-11 Hiroshi Kuwajima , Masayuki Tanaka

We verify the inductive McKay condition for simple groups of Lie type C, namely finite projective symplectic groups. This contributes to the program of a complete proof of the McKay conjecture for all finite groups via the reduction theorem…

Representation Theory · Mathematics 2016-12-13 Marc Cabanes , Britta Späth

We prove finiteness properties for groups of homeomorphisms that have finitely many "singular points", and we describe the normal structure of such groups. As an application, we prove that every countable abelian group can be embedded into…

Group Theory · Mathematics 2024-07-04 James Belk , James Hyde , Francesco Matucci

Groups - social communities are important components of entire societies, analysed by means of the social network concept. Their immanent feature is continuous evolution over time. If we know how groups in the social network has evolved we…

Social and Information Networks · Computer Science 2012-10-19 Piotr Bródka , Przemysław Kazienko , Bartosz Kołoszczyk

There has been considerable interest in recent decades in questions of random generation of finite and profinite groups, and finite simple groups in particular. In this paper we study similar notions for finite and profinite associative…

Rings and Algebras · Mathematics 2024-02-21 Damian Sercombe , Aner Shalev

This paper describes a design that can be used for Explainable AI. The lower level is a nested ensemble of patterns created by self-organisation. The upper level is a hierarchical tree, where nodes are linked through individual concepts, so…

Artificial Intelligence · Computer Science 2020-11-30 Kieran Greer

It is well known that the proportion of pairs of elements of $\operatorname{SL}(n,q)$ which generate the group tends to $1$ as $q^n\to \infty$. This was proved by Kantor and Lubotzky using the classification of finite simple groups. We give…

Group Theory · Mathematics 2021-07-20 Sean Eberhard , Stefan-C. Virchow

Feature selection can facilitate the learning of mixtures of discrete random variables as they arise, e.g. in crowdsourcing tasks. Intuitively, not all workers are equally reliable but, if the less reliable ones could be eliminated, then…

Machine Learning · Statistics 2017-11-28 Vincent Zhao , Steven W. Zucker

Generative neural networks are able to mimic intricate probability distributions such as those of handwritten text, natural images, etc. Since their inception several models were proposed. The most successful of these were based on…

Machine Learning · Computer Science 2024-09-18 Daniel N. Nissani

Recent work has applied supervised deep learning to derive continuous symmetry transformations that preserve the data labels and to obtain the corresponding algebras of symmetry generators. This letter introduces two improved algorithms…

High Energy Physics - Theory · Physics 2023-07-12 Roy T. Forestano , Konstantin T. Matchev , Katia Matcheva , Alexander Roman , Eyup B. Unlu , Sarunas Verner

When it is ethical and legal to use a sensitive attribute (such as gender or race) in machine learning systems, the question remains how to do so. We show that the naive application of machine learning algorithms using sensitive features…

Machine Learning · Computer Science 2017-07-21 Cynthia Dwork , Nicole Immorlica , Adam Tauman Kalai , Max Leiserson

We give an efficient algorithm to randomly generate finitely generated subgroups of a given size, in a finite rank free group. Here, the size of a subgroup is the number of vertices of its representation by a reduced graph such as can be…

Group Theory · Mathematics 2010-06-21 Frédérique Bassino , Cyril Nicaud , Pascal Weil

We introduce a theory-driven mechanism for learning a neural network model that performs generative topology design in one shot given a problem setting, circumventing the conventional iterative process that computational design tasks…

Machine Learning · Computer Science 2018-12-31 Ruijin Cang , Hope Yao , Yi Ren

Probabilistic algorithms are applied to prove theorems about the finite general linear and unitary groups which are typically proved by techniques such as character theory and Moebius inversion. Among the theorems studied are Steinberg's…

Group Theory · Mathematics 2007-05-23 Jason Fulman

We investigate the computational complexity for determining various properties of a finite transformation semigroup given by generators. We introduce a simple framework to describe transformation semigroup properties that are decidable in…

Group Theory · Mathematics 2024-11-26 Lukas Fleischer , Trevor Jack