arXiv Machine Learning June 4, 2026 By Vincent B\"urgin, Daniel Herbst, Ya-Wei Eileen Lin, Stefanie Jegelka

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

Read the original on arXiv Machine Learning →

arXiv:2606. 04754v1 Announce Type: new Abstract: Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter symmetries: transformations that leave the realized function unchanged.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jul 7

A Complete Symmetry Classification of Shallow ReLU Networks

arXiv:2604. 14037v2 Announce Type: replace Abstract: Parameter space is not function space for neural network architectures.

By Pranavkrishnan Ramakrishnan

arXiv Machine Learning

Jun 10

Conservation Laws from Data Symmetry in Neural Networks

arXiv:2606. 10913v1 Announce Type: new Abstract: We explore whether intrinsic symmetries of the training data lead to conserved quantities during gradient-flow training of neural networks.

By Jakob Galley, Vahid Shahverdi, Axel Flinth

Hugging Face Trending Papers

Aug 12

Reducing Symmetry Increase in Equivariant Neural Networks

Equivariant Neural Networks (ENNs) have empowered numerous applications in scientific fields. Despite their remarkable capacity for representing geometric structures, ENNs suffer from degraded expressivity when processing symmetric inputs: the output representations are invariant to transformations that extend beyond the input's symmetries.

arXiv Machine Learning

6d ago

Reducing Symmetry Increase in Equivariant Neural Networks

arXiv:2608. 12010v1 Announce Type: new Abstract: Equivariant Neural Networks (ENNs) have empowered numerous applications in scientific fields.

By Ning Lin, Jiacheng Cen, Anyi Li, Wenbing Huang, Hao Sun

arXiv Machine Learning

Jul 10

Explaining Near-Zero Hessian Eigenvalues Through Approximate Symmetries in Neural Networks

arXiv:2607. 07845v1 Announce Type: new Abstract: The Hessian of the training loss governs the local geometry of the loss landscape, yet despite existing explanations for its largest eigenvalues, the origin of the vast multitude of vanishingly small eigenvalues remains elusive.

By Marcel K\"uhn, Bernd Rosenow

arXiv Machine Learning

Aug 10

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data

arXiv:2511. 09432v2 Announce Type: replace Abstract: Machine learning (ML) models achieve remarkable performance but remain hard to interpret due to their scale and complexity.

By Ege Erdogan, Ana Lucic

safety

Related stories

A Complete Symmetry Classification of Shallow ReLU Networks

Conservation Laws from Data Symmetry in Neural Networks

Reducing Symmetry Increase in Equivariant Neural Networks

Reducing Symmetry Increase in Equivariant Neural Networks

Explaining Near-Zero Hessian Eigenvalues Through Approximate Symmetries in Neural Networks

Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data