Cover Image

A solvable model of learning generative diffusion: theory and insights

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cui, Hugo, Pehlevan, Cengiz, Lu, Yue M.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Disordered Systems and Neural Networks
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Asymptotic theory of in-context learning by linear attention
by: Lu, Yue M., et al.
Published: (2024)

Adaptive kernel predictors from feature-learning infinite limits of neural networks
by: Lauditi, Clarissa, et al.
Published: (2025)

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
by: Bordelon, Blake, et al.
Published: (2025)

Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning
by: Bordelon, Blake, et al.
Published: (2026)

Nadaraya-Watson kernel smoothing as a random energy model
by: Zavatone-Veth, Jacob A., et al.
Published: (2024)

A Dynamical Model of Neural Scaling Laws
by: Bordelon, Blake, et al.
Published: (2024)

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

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

Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time
by: Bordelon, Blake, et al.
Published: (2025)

Infinite Limits of Multi-head Transformer Dynamics
by: Bordelon, Blake, et al.
Published: (2024)

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles
by: Ruben, Benjamin S., et al.
Published: (2023)

Risk and cross validation in ridge regression with correlated samples
by: Atanasov, Alexander, et al.
Published: (2024)

Scaling and renormalization in high-dimensional regression
by: Atanasov, Alexander, et al.
Published: (2024)

Grokking as the Transition from Lazy to Rich Training Dynamics
by: Kumar, Tanishq, et al.
Published: (2023)

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

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

How does training shape the Riemannian geometry of neural network representations?
by: Zavatone-Veth, Jacob A., et al.
Published: (2023)

Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models
by: Atanasov, Alexander, et al.
Published: (2025)

A note on the dynamics of extended-context disordered kinetic spin models
by: Zavatone-Veth, Jacob A., et al.
Published: (2025)

High-dimensional learning of narrow neural networks
by: Cui, Hugo
Published: (2024)

Dynamically Learning to Integrate in Recurrent Neural Networks
by: Bordelon, Blake, et al.
Published: (2025)

Asymptotics of feature learning in two-layer networks after one gradient-step
by: Cui, Hugo, et al.
Published: (2024)

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization
by: Mendes, Vicente Conde, et al.
Published: (2026)

Non-equilibrium active noise enhances generative memory in diffusion models
by: Behera, Agnish Kumar, et al.
Published: (2024)

Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds
by: Troiani, Emanuele, et al.
Published: (2025)

Bias-inducing geometries: an exactly solvable data model with fairness implications
by: Mannelli, Stefano Sarao, et al.
Published: (2022)

An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem
by: Nam, Yoonsoo, et al.
Published: (2024)

Applying statistical learning theory to deep learning
by: Gerbelot, Cédric, et al.
Published: (2023)

Nonequilbrium physics of generative diffusion models
by: Yu, Zhendong, et al.
Published: (2024)

High-dimensional Asymptotics of Denoising Autoencoders
by: Cui, Hugo, et al.
Published: (2023)

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

Specialization of softmax attention heads: insights from the high-dimensional single-location model
by: Sagitova, M., et al.
Published: (2026)

Discrete generative diffusion models without stochastic differential equations: a tensor network approach
by: Causer, Luke, et al.
Published: (2024)

Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions
by: Keup, Christian, et al.
Published: (2024)

Generative diffusion for perceptron problems: statistical physics analysis and efficient algorithms
by: Demyanenko, Elizaveta, et al.
Published: (2025)

Deep neural networks from the perspective of ergodic theory
by: Zhang, Fan
Published: (2023)

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

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

On learning higher-order cumulants in diffusion models
by: Aarts, Gert, et al.
Published: (2024)

Machine learning the Ising transition: A comparison between discriminative and generative approaches
by: Zhang, Difei, et al.
Published: (2024)