On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “GENEOs”

A topological model for partial equivariance in deep learning and data analysisstat.ML

Proposes a topological model for partial equivariance in neural networks.

problem Capturing partial equivariance in neural networks for data analysis.

method Introduces P-GENEOs and studies spaces of measurements and P-GENEOs between them.

result Spaces of measurements and P-GENEOs have convenient approximation and convexity properties.

partial equivariance neural networks topology data analysis GENEOs

2023-08-25abs ↗pdf ↗

Towards a topological-geometrical theory of group equivariant non-expansive operators for data analysis and machine learningcs.LG

The aim of this paper is to provide a general mathematical framework for group equivariance in the machine learning context. The framework builds on a synergy between persistent homology and the theory of group actions. We define group-equivariant non-expansive operators (GENEOs), which are maps between function spaces…

2018-12-31abs ↗pdf ↗

Mathematical Foundation of Interpretable Equivariant Surrogate Modelsstat.ML

Paper defines mathematical framework for neural network explainability.

problem Neural network explainability and equivariant operators.

method Mathematical framework based on Group Equivariant Non-Expansive Operators (GENEOs) and complexity measures.

result Formal properties and interpretability of Group Equivariant Operators (GEOs) defined.

explainability neural networks equivariant operators Group Equivariant Non-Expansive Operators (GENEOs)complexity measures

2025-03-03abs ↗pdf ↗

Low-Resource White-Box Semantic Segmentation of Supporting Towers on 3D Point Clouds via Signature Shape Identificationcs.CV

SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.

problem Lack of resources and transparency in 3D semantic segmentation models.

method SCENE-Net uses signature shapes identified via GENEOs to achieve semantic segmentation with minimal resources.

result SCENE-Net achieves comparable IoU to state-of-the-art methods with less data and computational resources.

3D point cloud semantic segmentation white-box model signature shapes group equivariant operators

2023-06-13abs ↗pdf ↗