Image de couverture de livre

Kernel Renormalization in Bayesian Deep Neural Networks: the Equivalent Wishart Ansatz in the Proportional Regime

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Baglioni, Paolo, Keup, Christian, Zimbardo, Vincenzo, Pacelli, Rosalba, Vezzani, Alessandro, Burioni, Raffaella, Rotondo, Pietro
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Disordered Systems and Neural Networks
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Kernel shape renormalization explains output-output correlations in finite Bayesian one-hidden-layer networks
par: Baglioni, P., et autres
Publié: (2024)

Predictive power of a Bayesian effective action for fully-connected one hidden layer neural networks in the proportional limit
par: Baglioni, P., et autres
Publié: (2024)

Statistical mechanics of transfer learning in fully-connected networks in the proportional limit
par: Ingrosso, Alessandro, et autres
Publié: (2024)

Microscopic and collective signatures of feature learning in neural networks
par: Corti, Andrea, et autres
Publié: (2025)

Unveiling the Dimensionality of Networks of Networks
par: Grimaldi, Lorenzo, et autres
Publié: (2025)

A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit
par: Pacelli, R., et autres
Publié: (2022)

Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions
par: Keup, Christian, et autres
Publié: (2024)

Spectral properties of a Non-Hermitian extension of the diluted Wishart ensemble
par: Guzmán-González, Edgar, et autres
Publié: (2025)

Generalized Wilson-Cowan model with short term synaptic plasticity
par: Trabocchi, Tommaso, et autres
Publié: (2025)

The Wishart--Rosenzweig--Porter random matrix ensemble
par: Delapalme, Victor, et autres
Publié: (2025)

Proportional infinite-width infinite-depth limit for deep linear neural networks
par: Bassetti, Federico, et autres
Publié: (2024)

Renormalization group analysis of noisy neural field
par: Zang, Jie, et autres
Publié: (2025)

Top eigenpair statistics of diluted Wishart matrices
par: Budnick, Barak, et autres
Publié: (2025)

The quest for new materials: the network theory and machine learning perspectives
par: Moi, Jacopo, et autres
Publié: (2025)

Foundation Neural-Networks Quantum States as a Unified Ansatz for Multiple Hamiltonians
par: Rende, Riccardo, et autres
Publié: (2025)

Linking Network and Neuron-level Correlations by Renormalized Field Theory
par: Dick, Michael, et autres
Publié: (2023)

Renormalization group for deep neural networks: Universality of learning and scaling laws
par: Coppola, Gorka Peraza, et autres
Publié: (2025)

Renormalization Group flow, Optimal Transport and Diffusion-based Generative Model
par: Sheshmani, Artan, et autres
Publié: (2024)

Evidence of Scaling Regimes in the Hopfield Dynamics of Whole Brain Model
par: Gosti, Giorgio, et autres
Publié: (2024)

Renormalization group of topological scattering networks
par: Zhang, Zhe, et autres
Publié: (2024)

Renormalization of networks with weak geometric coupling
par: van der Kolk, Jasper, et autres
Publié: (2024)

Neural Projected Quantum Dynamics: a systematic study
par: Gravina, Luca, et autres
Publié: (2024)

Efficiency of the hidden fermion determinant states Ansatz in the light of different complexity measures
par: Wurst, Björn J., et autres
Publié: (2024)

Neural Network Ground State from the Neural Tangent Kernel Perspective: The Sign Bias
par: Kol-Namer, Harel, et autres
Publié: (2024)

Proportional asymptotics of piecewise exponential proportional hazards models
par: Massa, Emanuele
Publié: (2025)

Probing Band-center Anomaly with the Kernel Polynomial Method
par: Khan, N. A., et autres
Publié: (2019)

Electric Polarization from Many-Body Neural Network Ansatz
par: Li, Xiang, et autres
Publié: (2023)

Spin Hall Effect: Symmetry Breaking, Twisting, and Giant Disorder Renormalization
par: Perkins, David T. S., et autres
Publié: (2024)

Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers
par: Bassetti, Federico, et autres
Publié: (2024)

Unified Description of Learning Dynamics in the Soft Committee Machine from Finite to Ultra-Wide Regimes
par: Afanah, Assem, et autres
Publié: (2025)

Local sign stability and its implications for spectra of sparse random graphs and stability of ecosystems
par: Valigi, Pietro, et autres
Publié: (2023)

Exploring high-dimensional random landscapes: from spin glasses to random matrices, passing through simple chaotic systems
par: Pacco, Alessandro
Publié: (2025)

Wilsonian Renormalization of Neural Network Gaussian Processes
par: Howard, Jessica N., et autres
Publié: (2024)

Solving Classical and Quantum Spin Glasses with Deep Boltzmann Quantum States
par: Leone, Luca, et autres
Publié: (2026)

Scalable Neural Quantum State based Kernel Polynomial Method for Optical Properties from the First Principle
par: Liu, Wei, et autres
Publié: (2025)

Operator Learning Renormalization Group
par: Luo, Xiu-Zhe, et autres
Publié: (2024)

Higher-order Laplacian Renormalization
par: Nurisso, Marco, et autres
Publié: (2024)

Rapid Discovery of Graphene Nanocrystals Using DFT and Bayesian Optimization with Neural Network Kernel
par: Özönder, Şener, et autres
Publié: (2022)

Dynamical Regimes of Multimodal Diffusion Models
par: Albrychiewicz, Emil, et autres
Publié: (2026)

Renormalization-Group Analysis of the Many-Body Localization Transition in the Random-Field XXZ Chain
par: Niedda, Jacopo, et autres
Publié: (2024)