paper-with-me

홈 › Papers

Optimization Dynamics of Equivariant and Augmented Neural Networks

2023-03-23 · Oskar Nordenfors, Fredrik Ohlsson, Axel Flinth

We investigate the optimization of neural networks on symmetric data, and compare the strategy of constraining the architecture to be equivariant to that of using data augmentation. Our analysis reveals that that the relative geometry of the admissible and the equivariant layers, respectively, plays a key role. Under natural assumptions on the data, network, loss, and group of symmetries, we show that compatibility of the spaces of admissible layers and equivariant layers, in the sense that the corresponding orthogonal projections commute, implies that the sets of equivariant stationary points are identical for the two strategies. If the linear layers of the network also are given a unitary parametrization, the set of equivariant layers is even invariant under the gradient flow for augmented models. Our analysis however also reveals that even in the latter situation, stationary points may be unstable for augmented training although they are stable for the manifestly equivariant models.

📄 PDF Abstract BibTeX arXiv:2303.13458

Code (1)

usinedepain/eq_aug_dyn 공식 구현 pytorch

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Equivariant Neural Tangent Kernels

2024-06-10 · Philipp Misof, Pan Kessel, Jan E. Gerken

Little is known about the training dynamics of equivariant neural networks, in particular how it compares to data augmented training of their non-equivariant counterparts. Recently, neural tangent kernels (NTKs) have eme…

Data Augmentationimage-classificationImage ClassificationMedical Image Analysis+1

Time-Equivariant Contrastive Video Representation Learning

2021-12-07 · ICCV 2021 10 · Simon Jenni, Hailin Jin

We introduce a novel self-supervised contrastive learning method to learn representations from unlabelled videos. Existing approaches ignore the specifics of input distortions, e.g., by learning invariance to temporal tr…

Action RecognitionContrastive LearningRepresentation LearningRetrieval+1

Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

2026-01-03 · Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan, Yilun Du 외 arxiv

Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of external objects. These sensory streams an…

Rotation Equivariant Operators for Machine Learning on Scalar and Vector Fields

2021-08-21 · Paul Shen, Michael Herbst, Venkat Viswanathan

We develop theory and software for rotation equivariant operators on scalar and vector fields, with diverse applications in simulation, optimization and machine learning. Rotation equivariance (covariance) means all fiel…

BIG-bench Machine LearningTranslation

Equivariance and Augmentation for Bayesian Neural Networks

2026-06-24 · Miaowen Dong, Axel Flinth, Jan E. Gerken arxiv

Symmetries are important for many deep learning tasks, ranging from applications in the sciences to medical imaging. However, there is an ongoing debate about whether to impose symmetry constraints on the neural network …

Data Augmentation