Imagen de Portada

The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chizat, Lénaïc, Netrapalli, Praneeth
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning 68T07
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram
por: Chizat, Lénaïc
Publicado: (2025)

Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime
por: Chizat, Lénaïc, et al.
Publicado: (2025)

Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies
por: Chizat, Lénaïc, et al.
Publicado: (2026)

Hybrid deep additive neural networks
por: Kim, Gyu Min, et al.
Publicado: (2024)

Asymptotic convexity of wide and shallow neural networks
por: Borkar, Vivek, et al.
Publicado: (2025)

Bayesian sparsification for deep neural networks with Bayesian model reduction
por: Marković, Dimitrije, et al.
Publicado: (2023)

A Generalization Bound for a Family of Implicit Networks
por: Fung, Samy Wu, et al.
Publicado: (2024)

Dimensionality reduction and width of deep neural networks based on topological degree theory
por: Yang, Xiao-Song
Publicado: (2025)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
por: Yamchote, Phaphontee, et al.
Publicado: (2025)

Feature Learning Beyond the Edge of Stability
por: Terjék, Dávid
Publicado: (2025)

Segmentation of cracks in 3d images of fiber reinforced concrete using deep learning
por: Nowacka, Anna, et al.
Publicado: (2025)

Efficient kernel surrogates for neural network-based regression
por: Qadeer, Saad, et al.
Publicado: (2023)

Comparison of generalised additive models and neural networks in applications: A systematic review
por: Doohan, Jessica, et al.
Publicado: (2025)

Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids
por: Cho, Sung Woong, et al.
Publicado: (2024)

Annealed Sinkhorn for Optimal Transport: convergence, regularization path and debiasing
por: Chizat, Lénaïc
Publicado: (2024)

Overlap-aware meta-learning attention to enhance hypergraph neural networks for node classification
por: Yang, Murong, et al.
Publicado: (2025)

Explicit neural network classifiers for non-separable data
por: Ewald, Patrícia Muñoz
Publicado: (2025)

Spectral complexity of deep neural networks
por: Di Lillo, Simmaco, et al.
Publicado: (2024)

Deep linear networks for regression are implicitly regularized towards flat minima
por: Marion, Pierre, et al.
Publicado: (2024)

Learning time-scales in two-layers neural networks
por: Berthier, Raphaël, et al.
Publicado: (2023)

To be or not to be stable, that is the question: understanding neural networks for inverse problems
por: Evangelista, Davide, et al.
Publicado: (2022)

A scaled TW-PINN: A physics-informed neural network for traveling wave solutions of reaction-diffusion equations with general coefficients
por: Han, Seungwan, et al.
Publicado: (2026)

Generalization error bounds for two-layer neural networks with Lipschitz loss function
por: Nguwi, Jiang Yu, et al.
Publicado: (2026)

Genus expansion for non-linear random matrix ensembles with applications to neural networks
por: Cirone, Nicola Muca, et al.
Publicado: (2024)

Learning to Control the Smoothness of Graph Convolutional Network Features
por: Wang, Shih-Hsin, et al.
Publicado: (2024)

An in-depth look at approximation via deep and narrow neural networks
por: Dommel, Joris, et al.
Publicado: (2025)

Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
por: Pavlov, Gorgi
Publicado: (2026)

Conservative approximation-based feedforward neural network for WENO schemes
por: Park, Kwanghyuk, et al.
Publicado: (2025)

The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
por: Brännvall, Rickard, et al.
Publicado: (2023)

Feature Selection with Annealing for Forecasting Financial Time Series
por: Pabuccu, Hakan, et al.
Publicado: (2023)

Deep learning the Hurst parameter of linear fractional processes and assessing its reliability
por: Boros, Dániel, et al.
Publicado: (2024)

The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
por: Bastounis, Alexander, et al.
Publicado: (2023)

Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
por: Gonon, Lukas, et al.
Publicado: (2023)

Reconstructing shared dynamics with a deep neural network
por: Benkő, Zsigmond, et al.
Publicado: (2021)

Nonlocal techniques for the analysis of deep ReLU neural network approximations
por: Schneider, Cornelia, et al.
Publicado: (2025)

Convergence of gradient descent for deep neural networks
por: Chatterjee, Sourav
Publicado: (2022)

A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets
por: Tavakoli, Fatemeh, et al.
Publicado: (2023)

Graph-Conditional Flow Matching for Relational Data Generation
por: Scassola, Davide, et al.
Publicado: (2025)

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
por: Liu, Qiang, et al.
Publicado: (2024)

Optimizing Basis Function Selection in Constructive Wavelet Neural Networks and Its Applications
por: Huang, Dunsheng, et al.
Publicado: (2025)