Imagen de Portada

Parameter Symmetry Potentially Unifies Deep Learning Theory

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ziyin, Liu, Xu, Yizhou, Poggio, Tomaso, Chuang, Isaac
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Disordered Systems and Neural Networks Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Formation of Representations in Neural Networks
por: Ziyin, Liu, et al.
Publicado: (2024)

Heterosynaptic Circuits Are Universal Gradient Machines
por: Ziyin, Liu, et al.
Publicado: (2025)

A universal compression theory for lottery ticket hypothesis and neural scaling laws
por: Wang, Hong-Yi, et al.
Publicado: (2025)

Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
por: Ziyin, Liu, et al.
Publicado: (2025)

Proof of a perfect platonic representation hypothesis
por: Ziyin, Liu, et al.
Publicado: (2025)

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

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

Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics
por: Avidan, Yehonatan, et al.
Publicado: (2023)

Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
por: Lauditi, Clarissa, et al.
Publicado: (2026)

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
por: Xu, Yizhou, et al.
Publicado: (2025)

Approximation Theory for Neural Networks: Old and New
por: Mukherjee, Soumendu Sundar, et al.
Publicado: (2026)

Representation Learning on a Random Lattice
por: Brill, Aryeh
Publicado: (2025)

Grokking vs. Learning: Same Features, Different Encodings
por: Manning-Coe, Dmitry, et al.
Publicado: (2025)

Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
por: Kalra, Dayal Singh, et al.
Publicado: (2026)

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

Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning
por: Staats, Max, et al.
Publicado: (2023)

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

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator
por: Kantamneni, Subhash, et al.
Publicado: (2024)

KAN: Kolmogorov-Arnold Networks
por: Liu, Ziming, et al.
Publicado: (2024)

Training Dynamics of Nonlinear Contrastive Learning Model in the High Dimensional Limit
por: Meng, Lineghuan, et al.
Publicado: (2024)

Predictive Coding Networks and Inference Learning: Tutorial and Survey
por: van Zwol, Björn, et al.
Publicado: (2024)

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

Identifying internal patterns in (1+1)-dimensional directed percolation using neural networks
por: Parkhomenko, Danil, et al.
Publicado: (2025)

A Spin Glass Characterization of Neural Networks
por: Li, Jun
Publicado: (2025)

Towards Distributed Neural Architectures
por: Cowsik, Aditya, et al.
Publicado: (2025)

A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs
por: Kalra, Dayal Singh, et al.
Publicado: (2026)

A method for quantifying the generalization capabilities of generative models for solving Ising models
por: Ma, Qunlong, et al.
Publicado: (2024)

On the origin of neural scaling laws: from random graphs to natural language
por: Barkeshli, Maissam, et al.
Publicado: (2026)

The Persian Rug: solving toy models of superposition using large-scale symmetries
por: Cowsik, Aditya, et al.
Publicado: (2024)

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

Smooth Kolmogorov Arnold networks enabling structural knowledge representation
por: Samadi, Moein E., et al.
Publicado: (2024)

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

A Theory of Saddle Escape in Deep Nonlinear Networks
por: Rawal, Divit, et al.
Publicado: (2026)

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
por: Nishiyama, Sota, et al.
Publicado: (2025)

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

Nature-Inspired Local Propagation
por: Betti, Alessandro, et al.
Publicado: (2024)

Preisach Attention: A Hysteretic Model of Sequential Memory
por: Frydrych, Piotr
Publicado: (2026)

Graph Learning Metallic Glass Discovery from Wikipedia
por: Ouyang, K. -C., et al.
Publicado: (2025)

Exploring the Energy Landscape of RBMs: Reciprocal Space Insights into Bosons, Hierarchical Learning and Symmetry Breaking
por: Toledo-Marin, J. Quetzalcóatl, et al.
Publicado: (2025)

Lattice Protein Folding with Variational Annealing
por: Khandoker, Shoummo Ahsan, et al.
Publicado: (2025)