paper-with-me

홈 › Papers

A topological model for partial equivariance in deep learning and data analysis

2023-08-25 · Lucia Ferrari, Patrizio Frosini, Nicola Quercioli, Francesca Tombari

In this article, we propose a topological model to encode partial equivariance in neural networks. To this end, we introduce a class of operators, called P-GENEOs, that change data expressed by measurements, respecting the action of certain sets of transformations, in a non-expansive way. If the set of transformations acting is a group, then we obtain the so-called GENEOs. We then study the spaces of measurements, whose domains are subject to the action of certain self-maps, and the space of P-GENEOs between these spaces. We define pseudo-metrics on them and show some properties of the resulting spaces. In particular, we show how such spaces have convenient approximation and convexity properties.

📄 PDF Abstract BibTeX arXiv:2308.13357

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Partial Equivariances from Data

2021-10-19 · David W. Romero, Suhas Lohit

Group Convolutional Neural Networks (G-CNNs) constrain learned features to respect the symmetries in the selected group, and lead to better generalization when these symmetries appear in the data. If this is not the case…

Image ClassificationRotated MNIST

Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts

2024-07-05 · Hyunsu Kim, Yegon Kim, Hongseok Yang, Juho Lee

Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equivariance is fixed to the symmetry of th…

Variational Inference

A General Theory of Correct, Incorrect, and Extrinsic Equivariance

2023-03-08 · NeurIPS 2023 11

Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivaria…

PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions

2020-07-20 · ICML 2020 1 · Zhengyang Shen, Lingshen He, Zhouchen Lin, Jinwen Ma

Recent research has shown that incorporating equivariance into neural network architectures is very helpful, and there have been some works investigating the equivariance of networks under group actions. However, as digi…

image-classificationImage ClassificationRotated MNIST

Leveraging Equivariances and Symmetries in the Control Barrier Function Synthesis

2025-09-04 · Adrian Wiltz, Dimos V. Dimarogonas arxiv

The synthesis of Control Barrier Functions (CBFs) often involves demanding computations or a meticulous construction. However, structural properties of the system dynamics and constraints have the potential to mitigate t…