Cover Image

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rubin, Noa, Fischer, Kirsten, Lindner, Javed, Dahmen, David, Seroussi, Inbar, Ringel, Zohar, Krämer, Michael, Helias, Moritz
Format:	Preprint
Published:	2025
Subjects:	Disordered Systems and Neural Networks Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Critical feature learning in deep neural networks
by: Fischer, Kirsten, et al.
Published: (2024)

Applications of Statistical Field Theory in Deep Learning
by: Ringel, Zohar, et al.
Published: (2025)

Grokking as a First Order Phase Transition in Two Layer Networks
by: Rubin, Noa, et al.
Published: (2023)

Lecture notes: From Gaussian processes to feature learning
by: Helias, Moritz, et al.
Published: (2026)

Field theory for optimal signal propagation in ResNets
by: Fischer, Kirsten, et al.
Published: (2023)

Renormalization group for deep neural networks: Universality of learning and scaling laws
by: Coppola, Gorka Peraza, et al.
Published: (2025)

Dynamics of neural scaling laws in random feature regression with powerlaw-distributed kernel eigenvalues
by: Kramp, Jakob, et al.
Published: (2026)

Effect of Synaptic Heterogeneity on Neuronal Coordination
by: Layer, Moritz, et al.
Published: (2023)

Reduction of interaction order in hard combinatorial optimization via conditionally independent degrees of freedom
by: Ciobanu, Alexandru, et al.
Published: (2025)

Linking Network and Neuron-level Correlations by Renormalized Field Theory
by: Dick, Michael, et al.
Published: (2023)

A unified theory of feature learning in RNNs and DNNs
by: Bauer, Jan P., et al.
Published: (2026)

Algorithmic Task Capture, Computational Complexity, and Inductive Bias of Infinite Transformers
by: Davidovich, Orit, et al.
Published: (2026)

Demystifying Spectral Bias on Real-World Data
by: Lavie, Itay, et al.
Published: (2024)

Beyond-mean-field fluctuations for the solution of constraint satisfaction problems
by: Foos, Niklas, et al.
Published: (2025)

Towards Understanding Inductive Bias in Transformers: A View From Infinity
by: Lavie, Itay, et al.
Published: (2024)

Graph Neural Networks Do Not Always Oversmooth
by: Epping, Bastian, et al.
Published: (2024)

Statistical physics through the lens of real-space mutual information
by: Gökmen, Doruk Efe, et al.
Published: (2021)

Compression theory for inhomogeneous systems
by: Gökmen, Doruk Efe, et al.
Published: (2023)

Wilsonian Renormalization of Neural Network Gaussian Processes
by: Howard, Jessica N., et al.
Published: (2024)

Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
by: Bordelon, Blake, et al.
Published: (2026)

No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions
by: Ruben, Benjamin S., et al.
Published: (2024)

Asymmetric Scaling Laws from Sparse Features
by: Sous, John, et al.
Published: (2026)

Pattern Expansion of Spin Glasses
by: Shen, Mutian, et al.
Published: (2026)

How Feature Learning Can Improve Neural Scaling Laws
by: Bordelon, Blake, et al.
Published: (2024)

Identifying the impact of local connectivity patterns on dynamics in excitatory-inhibitory networks
by: Shao, Yuxiu, et al.
Published: (2024)

Improving CFT Operators Using Machine Learning
by: Oppenheim, Lior, et al.
Published: (2026)

Graph-Based Feature Engineering to Predict the Dynamical Properties of Condensed Matter
by: Wang, An, et al.
Published: (2024)

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
by: Dandi, Yatin, et al.
Published: (2026)

Impact of heavy-tailed synaptic strength distributions on self-sustained activity in networks of spiking neurons
by: Tönjes, Ralf, et al.
Published: (2026)

Mitigating the Curse of Detail: Scaling Arguments for Feature Learning and Sample Complexity
by: Rubin, Noa, et al.
Published: (2025)

Random Features Hopfield Networks generalize retrieval to previously unseen examples
by: Kalaj, Silvio, et al.
Published: (2024)

Probing Band-center Anomaly with the Kernel Polynomial Method
by: Khan, N. A., et al.
Published: (2019)

From Embeddings to Dyson Series: Transformer Mechanics as Non-Hermitian Operator Theory
by: Chang, Po-Hao
Published: (2026)

Furutsu-Novikov--like cross-correlation--response relations for systems driven by shot noise
by: Stubenrauch, Jakob, et al.
Published: (2024)

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
by: Defilippis, Leonardo, et al.
Published: (2025)

Transfer Learning in Infinite Width Feature Learning Networks
by: Lauditi, Clarissa, et al.
Published: (2025)

Machine Learning the Operator Content of the Critical Self-Dual Ising-Higgs Gauge Model
by: Oppenheim, Lior, et al.
Published: (2023)

Kernel shape renormalization explains output-output correlations in finite Bayesian one-hidden-layer networks
by: Baglioni, P., et al.
Published: (2024)

Theory of coupled neuronal-synaptic dynamics
by: Clark, David G., et al.
Published: (2023)

Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
by: Veiga, Rodrigo, et al.
Published: (2024)