Imagen de Portada

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Boursier, Etienne, Pillaud-Vivien, Loucas, Flammarion, Nicolas
Formato:	Preprint
Publicado:	2022
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Simplicity bias and optimization threshold in two-layer ReLU networks
por: Boursier, Etienne, et al.
Publicado: (2024)

Convergence of Shallow ReLU Networks on Weakly Interacting Data
por: Dana, Léo, et al.
Publicado: (2025)

Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent
por: Schertzer, Adrien, et al.
Publicado: (2024)

Early alignment in two-layer networks training is a two-edged sword
por: Boursier, Etienne, et al.
Publicado: (2024)

Joint Learning in the Gaussian Single Index Model
por: Pillaud-Vivien, Loucas, et al.
Publicado: (2025)

Penalising the biases in norm regularisation enforces sparsity
por: Boursier, Etienne, et al.
Publicado: (2023)

Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias
por: Town, James, et al.
Publicado: (2026)

Weighted variation spaces and approximation by shallow ReLU networks
por: DeVore, Ronald, et al.
Publicado: (2023)

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

Variational Inference for Uncertainty Quantification: an Analysis of Trade-offs
por: Margossian, Charles C., et al.
Publicado: (2024)

Benign overfitting in leaky ReLU networks with moderate input dimension
por: Karhadkar, Kedar, et al.
Publicado: (2024)

Computational-Statistical Gaps in Gaussian Single-Index Models
por: Damian, Alex, et al.
Publicado: (2024)

Nonparametric regression using over-parameterized shallow ReLU neural networks
por: Yang, Yunfei, et al.
Publicado: (2023)

Optimal rates of approximation by shallow ReLU$^k$ neural networks and applications to nonparametric regression
por: Yang, Yunfei, et al.
Publicado: (2023)

On the existence of optimal shallow feedforward networks with ReLU activation
por: Dereich, Steffen, et al.
Publicado: (2023)

Gradient descent provably escapes saddle points in the training of shallow ReLU networks
por: Cheridito, Patrick, et al.
Publicado: (2022)

Oscillating solutions to the mean-field Langevin descent-ascent flow
por: Mourrat, Jean-Christophe, et al.
Publicado: (2026)

N-ReLU: Zero-Mean Stochastic Extension of ReLU
por: Manik, Md Motaleb Hossen, et al.
Publicado: (2025)

Topological obstruction to the training of shallow ReLU neural networks
por: Nurisso, Marco, et al.
Publicado: (2024)

Constraining the outputs of ReLU neural networks
por: Alexandr, Yulia, et al.
Publicado: (2025)

Toric geometry of ReLU neural networks
por: Fu, Yaoying
Publicado: (2025)

Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs
por: Dhayalkar, Sahil Rajesh
Publicado: (2025)

The Resurrection of the ReLU
por: Horuz, Coşku Can, et al.
Publicado: (2025)

Stably unactivated neurons in ReLU neural networks
por: Brownlowe, Natalie, et al.
Publicado: (2024)

The Geometry of ReLU Networks through the ReLU Transition Graph
por: Dhayalkar, Sahil Rajesh
Publicado: (2025)

MIQCQP reformulation of the ReLU neural networks Lipschitz constant estimation problem
por: Sbihi, Mohammed, et al.
Publicado: (2024)

On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
por: Dereich, Steffen, et al.
Publicado: (2023)

Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
por: Li, Yuanfan, et al.
Publicado: (2025)

Solving the Poisson Equation with Dirichlet data by shallow ReLU$^α$-networks: A regularity and approximation perspective
por: Vaishampayan, Malhar, et al.
Publicado: (2024)

On learning Gaussian multi‐index models with gradient flow part I: General properties and two‐timescale learning
por: Alberto Bietti, et al.
Publicado: (2025)

Generalization analysis with deep ReLU networks for metric and similarity learning
por: Zhou, Junyu, et al.
Publicado: (2024)

An analysis of optimization problems involving ReLU neural networks
por: Plate, Christoph, et al.
Publicado: (2025)

On the algorithmic construction of deep ReLU networks
por: Huybrechs, Daan
Publicado: (2025)

Agnostic Learning of General ReLU Activation Using Gradient Descent
por: Awasthi, Pranjal, et al.
Publicado: (2022)

Complexity of One-Dimensional ReLU DNNs
por: Kogan, Jonathan, et al.
Publicado: (2025)

Symmetric Matrix Completion with ReLU Sampling
por: Liu, Huikang, et al.
Publicado: (2024)

Explicit integral representations and quantitative bounds for two-layer ReLU networks
por: Lee, Anthony
Publicado: (2026)

Minimum width for universal approximation using ReLU networks on compact domain
por: Kim, Namjun, et al.
Publicado: (2023)

Two-hidden-layer ReLU neural networks and finite elements
por: Jin, Pengzhan
Publicado: (2024)

Deep-ICE: the first globally optimal algorithm for minimizing 0-1 loss in two-layer ReLU and maxout networks
por: He, Xi, et al.
Publicado: (2025)