Imagen de Portada

Shallow diffusion networks provably learn hidden low-dimensional structure

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Boffi, Nicholas M., Jacot, Arthur, Tu, Stephen, Ziemann, Ingvar
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning with little mixing
por: Ziemann, Ingvar, et al.
Publicado: (2022)

A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning
por: Ziemann, Ingvar
Publicado: (2024)

Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
por: Ziemann, Ingvar, et al.
Publicado: (2024)

Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems
por: Ziemann, Ingvar, et al.
Publicado: (2022)

Nearly Instance-Optimal Parameter Recovery from Many Trajectories via Hellinger Localization
por: Shekhtman, Eliot, et al.
Publicado: (2025)

State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?
por: Ziemann, Ingvar, et al.
Publicado: (2024)

Rate-Optimal Non-Asymptotics for the Quadratic Prediction Error Method
por: Stamouli, Charis, et al.
Publicado: (2024)

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
por: Jacot, Arthur
Publicado: (2023)

Polynomial Speedup in Diffusion Models with the Multilevel Euler-Maruyama Method
por: Jacot, Arthur
Publicado: (2026)

Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets
por: Jacot, Arthur
Publicado: (2025)

Logarithmic Regret for Nonlinear Control
por: Wang, James, et al.
Publicado: (2025)

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
por: Tu, Zhenfeng, et al.
Publicado: (2024)

DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel
por: Dupuis, Benjamin, et al.
Publicado: (2021)

Active Learning for Control-Oriented Identification of Nonlinear Systems
por: Lee, Bruce D., et al.
Publicado: (2024)

Model-free learning of probability flows: Elucidating the nonequilibrium dynamics of flocking
por: Boffi, Nicholas M., et al.
Publicado: (2024)

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
por: Jacot, Arthur, et al.
Publicado: (2024)

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
por: Wen, Yuxiao, et al.
Publicado: (2024)

A Vector Bernstein Inequality for Self-Normalized Martingales
por: Ziemann, Ingvar
Publicado: (2024)

An Elementary Proof of the Hanson-Wright Inequality
por: Ziemann, Ingvar
Publicado: (2025)

Unrolled denoising networks provably learn optimal Bayesian inference
por: Karan, Aayush, et al.
Publicado: (2024)

Deep learning probability flows and entropy production rates in active matter
por: Boffi, Nicholas M., et al.
Publicado: (2023)

Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
por: Zhang, Thomas T., et al.
Publicado: (2024)

Dynamical simulation via quantum machine learning with provable generalization
por: Gibbs, Joe, et al.
Publicado: (2022)

A Tutorial on the Non-Asymptotic Theory of System Identification
por: Ziemann, Ingvar, et al.
Publicado: (2023)

Linear Recursive Feature Machines provably recover low-rank matrices
por: Radhakrishnan, Adityanarayanan, et al.
Publicado: (2024)

Quantum automated learning with provable and explainable trainability
por: Ye, Qi, et al.
Publicado: (2025)

First-order ANIL provably learns representations despite overparametrization
por: Yüksel, Oğuz Kaan, et al.
Publicado: (2023)

Nonconvex Linear System Identification with Minimal State Representation
por: Tadipatri, Uday Kiran Reddy, et al.
Publicado: (2025)

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
por: Jacot, Arthur, et al.
Publicado: (2024)

Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
por: Bantzis, Ioannis, et al.
Publicado: (2025)

Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data
por: Delrocq, Ariane, et al.
Publicado: (2026)

Test-time scaling of diffusions with flow maps
por: Sabour, Amirmojtaba, et al.
Publicado: (2025)

Entanglement-induced provable and robust quantum learning advantages
por: Zhao, Haimeng, et al.
Publicado: (2024)

Residual connections provably mitigate oversmoothing in graph neural networks
por: Chen, Ziang, et al.
Publicado: (2025)

Flow map matching with stochastic interpolants: A mathematical framework for consistency models
por: Boffi, Nicholas M., et al.
Publicado: (2024)

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
por: Jacot, Arthur, et al.
Publicado: (2024)

Normalizing self-supervised learning for provably reliable Change Point Detection
por: Bazarova, Alexandra, et al.
Publicado: (2024)

Equivariant score-based generative models provably learn distributions with symmetries efficiently
por: Chen, Ziyu, et al.
Publicado: (2024)

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
por: Lee, Jason D., et al.
Publicado: (2024)

On provable privacy vulnerabilities of graph representations
por: Wu, Ruofan, et al.
Publicado: (2024)