arXiv Machine Learning July 16, 2026 By Zachary P. Bradshaw

What Your Model Threw Away and Why You'll Want It Back: Masking, Fingerprinting, and Privacy from Discarded Geometry

Read the original on arXiv Machine Learning →

arXiv:2607. 13046v1 Announce Type: new Abstract: We develop a framework for the information discarded by machine learning models whose inputs carry a Lie group action.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 13

Group Invariant Spectral Embedding

arXiv:2607. 08987v1 Announce Type: new Abstract: Spectral embedding methods are widely used for dimensionality reduction and clustering of high-dimensional datasets with intrinsic low-dimensional structures.

By Yeari Vigder, Paulina Hoyos, David Thong, Joakim and\'en, Joe Kileel, Amit Moscovich

rag

arXiv Machine Learning

Jun 19

The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups

arXiv:2606. 20547v1 Announce Type: new Abstract: We place the attention token on the group: a token is an element $g_i$ of a matrix Lie group $G$ -- a bare transformation, with no feature payload and no external action $\rho(g)$ carrying it.

By Przemyslaw Musialski

arXiv Machine Learning

Sep 10

Efficient Learning and Symmetry Discovery under Exact Invariances

arXiv:2609.07031v1 Announce Type: new Abstract: Learning with group invariances is central to many scientific and geometric learning problems, yet its computational foundations remain poorly understo...

By Ashkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet, Stefanie Jegelka

arXiv Machine Learning

Jul 30

Exact Symmetry as Algebra: A Machine-Verified Tensor Calculus that Enforces Physical Selection Rules

arXiv:2605. 20440v2 Announce Type: replace Abstract: Symmetry is central to the physical sciences, yet machine learning usually captures it only approximately, leaving a residual per-step equivariance error $\varepsilon$ that compounds with depth $M$ as $M\varepsilon$, whereas exact equivariance holds at unbounded depth; we demonstrate this divergence at fourteen orders of magnitude.

By Paulina Hoyos, Shashanka Ubaru, Dongsung Huh, Vasileios Kalantzis, Kenneth L. Clarkson, Misha Kilmer, Haim Avron, Lior Horesh

arXiv Machine Learning

Aug 26

Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity

arXiv:2608.24700v1 Announce Type: new Abstract: When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter sp...

By Alan Muriithi, Vedanta Thapar, Torben Berndt

arXiv Machine Learning

Jun 24

Data Augmentation: A Fourier Analysis Perspective

arXiv:2606. 24418v1 Announce Type: new Abstract: Data augmentation is a simple and model-agnostic approach for exploiting known invariances in learning problems.

By Behrooz Tahmasebi, Melanie Weber, Stefanie Jegelka

One email a morning, machine-written

Related stories

Group Invariant Spectral Embedding

The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups

Efficient Learning and Symmetry Discovery under Exact Invariances

Exact Symmetry as Algebra: A Machine-Verified Tensor Calculus that Enforces Physical Selection Rules

Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity

Data Augmentation: A Fourier Analysis Perspective