Cover Image

Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Hashimoto, Ichiro
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Statistics Theory 68T07 (primary)
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Super-fast Rates of Convergence for Neural Network Classifiers under the Hard Margin Condition
by: Tepakbong, Nathanael, et al.
Published: (2025)

Large Deviations of Gaussian Neural Networks with ReLU activation
by: Vogel, Quirin
Published: (2024)

Is ReLU Adversarially Robust?
by: Sooksatra, Korn, et al.
Published: (2024)

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

On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing
by: Behboodi, Arash, et al.
Published: (2024)

Universality of Benign Overfitting in Binary Linear Classification
by: Hashimoto, Ichiro, et al.
Published: (2025)

The minimal width of universal $p$-adic ReLU neural networks
by: Kiss, Sándor Z., et al.
Published: (2026)

Equidistribution-based training of Free Knot Splines and ReLU Neural Networks
by: Appella, Simone, et al.
Published: (2024)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
by: Frei, Spencer, et al.
Published: (2022)

Covering Numbers for Deep ReLU Networks with Applications to Function Approximation and Nonparametric Regression
by: Ou, Weigutian, et al.
Published: (2024)

On the algorithmic construction of deep ReLU networks
by: Huybrechs, Daan
Published: (2025)

Dense ReLU Neural Networks for Temporal-spatial Model
by: Padilla, Carlos Misael Madrid, et al.
Published: (2024)

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

Theoretical Compression Bounds for Wide Multilayer Perceptrons
by: Cheairi, Houssam El, et al.
Published: (2025)

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for space-time solutions of semilinear partial differential equations
by: Ackermann, Julia, et al.
Published: (2024)

Efficient Approximation to Analytic and $L^p$ functions by Height-Augmented ReLU Networks
by: Li, ZeYu, et al.
Published: (2026)

A Complete Symmetry Classification of Shallow ReLU Networks
by: Ramakrishnan, Pranavkrishnan
Published: (2026)

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

Deep neural networks with ReLU, leaky ReLU, and softplus activation provably overcome the curse of dimensionality for Kolmogorov partial differential equations with Lipschitz nonlinearities in the $L^p$-sense
by: Ackermann, Julia, et al.
Published: (2023)

Automated Code Generation and Validation for Software Components of Microcontrollers
by: Haug, Sebastian, et al.
Published: (2025)

Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation
by: Li, Li'ang, et al.
Published: (2023)

Adversarial Subspace Generation for Outlier Detection in High-Dimensional Data
by: Cribeiro-Ramallo, Jose, et al.
Published: (2025)

From Tempered to Benign Overfitting in ReLU Neural Networks
by: Kornowski, Guy, et al.
Published: (2023)

Combinatorial Regularity for Relatively Perfect Discrete Morse Gradient Vector Fields of ReLU Neural Networks
by: Brooks, Robyn, et al.
Published: (2024)

Constructive Universal Approximation and Finite Sample Memorization by Narrow Deep ReLU Networks
by: Hernández, Martín, et al.
Published: (2024)

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

Functional dimension of feedforward ReLU neural networks
by: Grigsby, J. Elisenda, et al.
Published: (2022)

Exact ReLU realization of tensor-product refinement iterates
by: Gantumur, Tsogtgerel
Published: (2026)

Approximation Error and Complexity Bounds for ReLU Networks on Low-Regular Function Spaces
by: Davis, Owen, et al.
Published: (2024)

Optimal In-context Adaptivity and Distributional Robustness of Transformers
by: Ma, Tianyi, et al.
Published: (2025)

Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers
by: Ching, Michelle, et al.
Published: (2026)

Component-based Sketching for Deep ReLU Nets
by: Wang, Di, et al.
Published: (2024)

On the minimax optimality of Flow Matching through the connection to kernel density estimation
by: Kunkel, Lea, et al.
Published: (2025)

Distribution estimation via Flow Matching with Lipschitz guarantees
by: Kunkel, Lea
Published: (2025)

Ensembles provably learn equivariance through data augmentation
by: Nordenfors, Oskar, et al.
Published: (2024)

ReLU neural network approximation to piecewise constant functions
by: Cai, Zhiqiang, et al.
Published: (2024)

Optimal estimation of a factorizable density using diffusion models with ReLU neural networks
by: Fan, Jianqing, et al.
Published: (2025)

Approximation and Gradient Descent Training with Neural Networks
by: Welper, G.
Published: (2024)

Function Gradient Approximation with Random Shallow ReLU Networks with Control Applications
by: Lamperski, Andrew, et al.
Published: (2024)

A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization
by: Dong, Lei
Published: (2026)