Image de couverture de livre

Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Avidan, Yehonatan, Li, Qianyi, Sompolinsky, Haim
Format:	Preprint
Publié:	2023
Sujets:	Machine Learning Disordered Systems and Neural Networks Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Coding schemes in neural networks learning classification tasks
par: van Meegen, Alexander, et autres
Publié: (2024)

Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
par: Tiberi, Lorenzo, et autres
Publié: (2024)

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
par: Defilippis, Leonardo, et autres
Publié: (2025)

Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
par: Lauditi, Clarissa, et autres
Publié: (2026)

Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
par: Di Carlo, Luca, et autres
Publié: (2025)

Parameter Symmetry Potentially Unifies Deep Learning Theory
par: Ziyin, Liu, et autres
Publié: (2025)

A Spin Glass Characterization of Neural Networks
par: Li, Jun
Publié: (2025)

Approximation Theory for Neural Networks: Old and New
par: Mukherjee, Soumendu Sundar, et autres
Publié: (2026)

Predictive Coding Graphs are a Superset of Feedforward Neural Networks
par: van Zwol, Björn
Publié: (2026)

Towards Distributed Neural Architectures
par: Cowsik, Aditya, et autres
Publié: (2025)

Simplified derivations for high-dimensional convex learning problems
par: Clark, David G., et autres
Publié: (2024)

KAN: Kolmogorov-Arnold Networks
par: Liu, Ziming, et autres
Publié: (2024)

Predictive Coding Networks and Inference Learning: Tutorial and Survey
par: van Zwol, Björn, et autres
Publié: (2024)

A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs
par: Kalra, Dayal Singh, et autres
Publié: (2026)

Representation Learning on a Random Lattice
par: Brill, Aryeh
Publié: (2025)

Applications of Statistical Field Theory in Deep Learning
par: Ringel, Zohar, et autres
Publié: (2025)

Grokking vs. Learning: Same Features, Different Encodings
par: Manning-Coe, Dmitry, et autres
Publié: (2025)

Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
par: Kalra, Dayal Singh, et autres
Publié: (2026)

Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning
par: Staats, Max, et autres
Publié: (2023)

A Geometric Perspective on the Difficulties of Learning GNN-based SAT Solvers
par: Skenderi, Geri
Publié: (2025)

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

Spectral Architecture Search for Neural Network Models
par: Peri, Gianluca, et autres
Publié: (2025)

Advantage of Quantum Neural Networks as Quantum Information Decoders
par: Zhong, Weishun, et autres
Publié: (2024)

Statistical Mechanics and Artificial Neural Networks: Principles, Models, and Applications
par: Böttcher, Lucas, et autres
Publié: (2024)

Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning
par: Bordelon, Blake, et autres
Publié: (2026)

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
par: Nishiyama, Sota, et autres
Publié: (2025)

Estimating Global Input Relevance and Enforcing Sparse Representations with a Scalable Spectral Neural Network Approach
par: Chicchi, Lorenzo, et autres
Publié: (2024)

Generalization through variance: how noise shapes inductive biases in diffusion models
par: Vastola, John J.
Publié: (2025)

Identifying internal patterns in (1+1)-dimensional directed percolation using neural networks
par: Parkhomenko, Danil, et autres
Publié: (2025)

A method for quantifying the generalization capabilities of generative models for solving Ising models
par: Ma, Qunlong, et autres
Publié: (2024)

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator
par: Kantamneni, Subhash, et autres
Publié: (2024)

On the origin of neural scaling laws: from random graphs to natural language
par: Barkeshli, Maissam, et autres
Publié: (2026)

The Persian Rug: solving toy models of superposition using large-scale symmetries
par: Cowsik, Aditya, et autres
Publié: (2024)

More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)
par: Meir, Sagi, et autres
Publié: (2026)

Smooth Kolmogorov Arnold networks enabling structural knowledge representation
par: Samadi, Moein E., et autres
Publié: (2024)

Grokking as Dimensional Phase Transition in Neural Networks
par: Wang, Ping
Publié: (2026)

High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
par: Ichikawa, Yuma, et autres
Publié: (2025)

Growing Neural Networks: Dynamic Evolution through Gradient Descent
par: Radhakrishnan, Anil, et autres
Publié: (2025)

Dynamical Mean-Field Theory of Self-Attention Neural Networks
par: Poc-López, Ángel, et autres
Publié: (2024)

Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches
par: Zambon, Alessandro, et autres
Publié: (2026)