Copertina

The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Levi, Noam, Oz, Yaron
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Disordered Systems and Neural Networks High Energy Physics - Theory Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Lecture Notes on Statistical Physics and Neural Networks
di: Hohm, Olaf
Pubblicazione: (2026)

Random matrix theory of sparse neuronal networks with heterogeneous timescales
di: Chotibut, Thiparat, et al.
Pubblicazione: (2025)

Neural Scaling Laws From Large-N Field Theory: Solvable Model Beyond the Ridgeless Limit
di: Zhang, Zhengkang
Pubblicazione: (2024)

The free energy limit of the SYK model at high temperature
di: Gamarnik, David, et al.
Pubblicazione: (2026)

Distributions of consecutive level spacings of circular unitary ensemble and their ratio: finite-size corrections and Riemann $ζ$ zeros
di: Nishigaki, Shinsuke M.
Pubblicazione: (2025)

Hofstadter's Butterfly in AdS$_3$ Black Holes
di: Ikeda, Kazuki, et al.
Pubblicazione: (2026)

Topological Effects in Neural Network Field Theory
di: Ferko, Christian, et al.
Pubblicazione: (2026)

Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy
di: Thurn, Yanick, et al.
Pubblicazione: (2024)

Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
di: He, Tianyu, et al.
Pubblicazione: (2024)

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

A Two-Phase Perspective on Deep Learning Dynamics
di: Koch, Robert de Mello, et al.
Pubblicazione: (2025)

Gauge-covariant stochastic neural fields: Stability and finite-width effects
di: Terin, Rodrigo Carmo
Pubblicazione: (2025)

Neural Network Quantum Field Theory from Transformer Architectures
di: Ageev, Dmitry S., et al.
Pubblicazione: (2026)

Bayesian RG Flow in Neural Network Field Theories
di: Howard, Jessica N., et al.
Pubblicazione: (2024)

Gaussian Universality of Perceptrons with Random Labels
di: Gerace, Federica, et al.
Pubblicazione: (2022)

Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model
di: Levi, Noam
Pubblicazione: (2026)

Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications
di: Xu, Yizhou, et al.
Pubblicazione: (2025)

Towards Worst-Case Guarantees with Scale-Aware Interpretability
di: Greenspan, Lauren, et al.
Pubblicazione: (2026)

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked models
di: Mergny, Pierre, et al.
Pubblicazione: (2024)

Grokking Modular Polynomials
di: Doshi, Darshil, et al.
Pubblicazione: (2024)

The neural networks with tensor weights and emergent fermionic Wick rules in the large-width limit
di: Huang, Guojun, et al.
Pubblicazione: (2025)

Analytic and numerical toolkit for the Anderson model in one dimension
di: Evnin, Oleg
Pubblicazione: (2025)

Learning topological defects formation with neural networks in a quantum phase transition
di: Shi, Han-Qing, et al.
Pubblicazione: (2022)

Probing the Latent Hierarchical Structure of Data via Diffusion Models
di: Sclocchi, Antonio, et al.
Pubblicazione: (2024)

A set of master variables for the two-star random graph
di: Akara-pipattana, Pawat, et al.
Pubblicazione: (2025)

Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
di: Levi, Noam, et al.
Pubblicazione: (2023)

Grokking at the Edge of Linear Separability
di: Beck, Alon, et al.
Pubblicazione: (2024)

Statistics of the Random Matrix Spectral Form Factor
di: Altland, Alex, et al.
Pubblicazione: (2025)

High-dimensional manifold of solutions in neural networks: insights from statistical physics
di: Malatesta, Enrico M.
Pubblicazione: (2023)

Binary perceptron computational gap -- a parametric fl RDT view
di: Stojnic, Mihailo
Pubblicazione: (2025)

Precise asymptotic analysis of Sobolev training for random feature models
di: Fisher, Katharine E, et al.
Pubblicazione: (2025)

Generalization performance of narrow one-hidden layer networks in the teacher-student setting
di: Ortiz, Rodrigo Pérez, et al.
Pubblicazione: (2025)

Exact capacity of the \emph{wide} hidden layer treelike neural networks with generic activations
di: Stojnic, Mihailo
Pubblicazione: (2024)

The twin peaks of learning neural networks
di: Demyanenko, Elizaveta, et al.
Pubblicazione: (2024)

Bayes-optimal learning of an extensive-width neural network from quadratically many samples
di: Maillard, Antoine, et al.
Pubblicazione: (2024)

Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection
di: Stojnic, Mihailo
Pubblicazione: (2026)

Fixed width treelike neural networks capacity analysis -- generic activations
di: Stojnic, Mihailo
Pubblicazione: (2024)

Capacity of the Hebbian-Hopfield network associative memory
di: Stojnic, Mihailo
Pubblicazione: (2024)

Parametric RDT approach to computational gap of symmetric binary perceptron
di: Stojnic, Mihailo
Pubblicazione: (2026)

Robust Reasoning as a Symmetry-Protected Topological Phase
di: Sung, Ilmo
Pubblicazione: (2026)