English
Related papers

Related papers: An Invitation to the Euler Characteristic Transfor…

200 papers

Cryo-electron tomography (Cryo-ET) is a 3D imaging technique that enables the systemic study of shape, abundance, and distribution of macromolecular structures in single cells in near-atomic resolution. However, the systematic and efficient…

Biomolecules · Quantitative Biology 2021-06-29 Kai Yi , Jianye Pang , Yungeng Zhang , Xiangrui Zeng , Min Xu

Real-world graphs naturally exhibit hierarchical or cyclical structures that are unfit for the typical Euclidean space. While there exist graph neural networks that leverage hyperbolic or spherical spaces to learn representations that embed…

Machine Learning · Computer Science 2023-09-11 Sungjun Cho , Seunghyuk Cho , Sungwoo Park , Hankook Lee , Honglak Lee , Moontae Lee

In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Yunlu Chen , Basura Fernando , Hakan Bilen , Matthias Nießner , Efstratios Gavves

We give explicit computations of the $\Gamma$-Euler characteristic of several families of orbit space definable translation groupoids. These include the translation groupoids associated to finite-dimensional linear representations of the…

Algebraic Topology · Mathematics 2025-08-27 Carla Farsi , Hannah Mobley , Christopher Seaton

Many new types of sensing or imaging surfaces are based on periodic thin films. It is explained how the response of those surfaces to partially coherent fields can be fully characterized by a set of functions in the wavenumber spectrum…

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both…

Machine Learning · Computer Science 2023-11-17 Clayton Sanford , Daniel Hsu , Matus Telgarsky

This paper explains how to use quantum field theory techniques to find formal power series that encode the virtual Euler characteristics of $\mathrm{Out}(F_n)$ and related graph complexes. Finding such power series was a necessary step in…

Group Theory · Mathematics 2025-04-23 Michael Borinsky , Karen Vogtmann

Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory. Attention is the power-house driving modern deep learning successes, but it lacks clear…

Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a novel method to embed directed acyclic graphs. Following prior…

Machine Learning · Computer Science 2018-06-08 Octavian-Eugen Ganea , Gary Bécigneul , Thomas Hofmann

Motivations like domain adaptation, transfer learning, and feature learning have fueled interest in inducing embeddings for rare or unseen words, n-grams, synsets, and other textual features. This paper introduces a la carte embedding, a…

Computation and Language · Computer Science 2018-05-16 Mikhail Khodak , Nikunj Saunshi , Yingyu Liang , Tengyu Ma , Brandon Stewart , Sanjeev Arora

Transformer-based models have achieved remarkable success, but their core components, Transformer layers, are largely heuristics-driven and engineered from the bottom up, calling for a prototypical model with high interpretability and…

Machine Learning · Computer Science 2025-06-02 Yunzhe Hu , Difan Zou , Dong Xu

Cryogenic electron microscopy (cryo-EM) provides a unique opportunity to study the structural heterogeneity of biomolecules. Being able to explain this heterogeneity with atomic models would help our understanding of their functional…

Electrical properties (EPs) of tissues, conductivity and permittivity, are modulated by the ionic and water content, which change in presence of pathologies. Information on tissues EPs can be used e.g. as an endogenous biomarker in…

Cryo-electron tomography (cryoET) is a technique that captures images of biological samples at different tilts, preserving their native state as much as possible. Along with the partial tilt series and noise, one of the major challenges in…

Signal Processing · Electrical Eng. & Systems 2023-07-26 Vinith Kishore , Valentin Debarnot , Ivan Dokmanić

In this paper we present a novel representation for deformation fields of 3D shapes, by considering the induced changes in the underlying metric. In particular, our approach allows to represent a deformation field in a coordinate-free way…

Graphics · Computer Science 2017-09-29 Etienne Corman , Maks Ovsjanikov

Assume that the coefficients of a polynomial in a complex variable are Laurent polynomials in some complex parameters. The parameter space (a complex torus) splits into strata corresponding to different combinations of coincidence of the…

Algebraic Geometry · Mathematics 2010-11-23 Gleb G. Gusev

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph…

Social and Information Networks · Computer Science 2018-04-11 William L. Hamilton , Rex Ying , Jure Leskovec

The variational properties of the scalar so--called ``Universal'' equations are reviewed and generalised. In particular, we note that contrary to earlier claims, each member of the Euler hierarchy may have an explicit field dependence. The…

High Energy Physics - Theory · Physics 2008-11-26 J. A. Mulvey

We propose an efficient semi-Lagrangian Characteristic Mapping (CM) method for solving the three-dimensional (3D) incompressible Euler equations. This method evolves advected quantities by discretizing the flow map associated with the…

Numerical Analysis · Mathematics 2023-02-21 Xi-Yuan Yin , Kai Schneider , Jean-Christophe Nave

We propose the Interferometric Graph Transform (IGT), which is a new class of deep unsupervised graph convolutional neural network for building graph representations. Our first contribution is to propose a generic, complex-valued spectral…

Machine Learning · Computer Science 2020-06-11 Edouard Oyallon