Cover Image

Breaking Data Symmetry is Needed For Generalization in Feature Learning Kernels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bernal, Marcel Tomàs, Mallinar, Neil Rohit, Belkin, Mikhail
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
by: Boix-Adsera, Enric, et al.
Published: (2025)

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
by: Mallinar, Neil, et al.
Published: (2024)

Benign, Tempered, or Catastrophic: A Taxonomy of Overfitting
by: Mallinar, Neil, et al.
Published: (2022)

Mirror Descent on Reproducing Kernel Banach Spaces
by: Kumar, Akash, et al.
Published: (2024)

On the Nystrom Approximation for Preconditioning in Kernel Machines
by: Abedsoltan, Amirhesam, et al.
Published: (2023)

Minimum-Norm Interpolation Under Covariate Shift
by: Mallinar, Neil, et al.
Published: (2024)

Symmetry-Breaking Descent for Invariant Cost Functionals
by: Osipov, Mikhail
Published: (2025)

Linear Recursive Feature Machines provably recover low-rank matrices
by: Radhakrishnan, Adityanarayanan, et al.
Published: (2024)

Eigenvectors of the De Bruijn Graph Laplacian: A Natural Basis for the Cut and Cycle Space
by: Philippakis, Anthony, et al.
Published: (2024)

General and Efficient Steering of Unconditional Diffusion
by: Wang, Qingsong, et al.
Published: (2026)

Context-Scaling versus Task-Scaling in In-Context Learning
by: Abedsoltan, Amirhesam, et al.
Published: (2024)

Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?
by: Abedsoltan, Amirhesam, et al.
Published: (2025)

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
by: Mirtaheri, Parsa, et al.
Published: (2026)

Learning Efficiency Meets Symmetry Breaking
by: Bai, Yingbin, et al.
Published: (2025)

On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory
by: Perin, Andrea, et al.
Published: (2024)

More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
by: Simon, James B., et al.
Published: (2023)

A Gap Between the Gaussian RKHS and Neural Networks: An Infinite-Center Asymptotic Analysis
by: Kumar, Akash, et al.
Published: (2025)

End-to-end Kernel Learning via Generative Random Fourier Features
by: Fang, Kun, et al.
Published: (2020)

Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders
by: Chanin, David, et al.
Published: (2025)

Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments
by: Chang, Junwoo, et al.
Published: (2025)

Fast training of large kernel models with delayed projections
by: Abedsoltan, Amirhesam, et al.
Published: (2024)

Average gradient outer product as a mechanism for deep neural collapse
by: Beaglehole, Daniel, et al.
Published: (2024)

xRFM: Accurate, scalable, and interpretable feature learning models for tabular data
by: Beaglehole, Daniel, et al.
Published: (2025)

Breaking Symmetry Bottlenecks in GNN Readouts
by: Talhi, Mouad, et al.
Published: (2026)

Symmetry Breaking and Equivariant Neural Networks
by: Kaba, Sékou-Oumar, et al.
Published: (2023)

Optimal Kernel Quantile Learning with Random Features
by: Wang, Caixing, et al.
Published: (2024)

Equivariant Symmetry Breaking Sets
by: Xie, YuQing, et al.
Published: (2024)

Learning Adapter Rank via Symmetry Breaking
by: Doyle, Cooper, et al.
Published: (2025)

Data-Aware Random Feature Kernel for Transformers
by: Farzam, Amirhossein, et al.
Published: (2026)

Improving Equivariant Networks with Probabilistic Symmetry Breaking
by: Lawrence, Hannah, et al.
Published: (2025)

To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
by: Lawrence, Hannah, et al.
Published: (2025)

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
by: Zhu, Libin, et al.
Published: (2023)

Quadratic models for understanding catapult dynamics of neural networks
by: Zhu, Libin, et al.
Published: (2022)

Breaking Symmetry When Training Transformers
by: Zuo, Chunsheng, et al.
Published: (2024)

Any-Subgroup Equivariant Networks via Symmetry Breaking
by: Goel, Abhinav, et al.
Published: (2026)

Symmetry-Aware Bayesian Optimization via Max Kernels
by: Bardou, Anthony, et al.
Published: (2025)

On the Intrinsic Dimensions of Data in Kernel Learning
by: Takhanov, Rustem
Published: (2026)

A Compositional Kernel Model for Feature Learning
by: Ruan, Feng, et al.
Published: (2025)

Fast Spectrum Estimation of Some Kernel Matrices
by: Lepilov, Mikhail
Published: (2024)

SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning
by: Yu, Qifan, et al.
Published: (2026)