Imagen de Portada

Memory capacity of two layer neural networks with smooth activations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Madden, Liam, Thrampoulidis, Christos
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning Optimization and Control 15A03, 26B10
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Interpolation with deep neural networks with non-polynomial activations: necessary and sufficient numbers of neurons
por: Madden, Liam
Publicado: (2024)

Next-token prediction capacity: general upper bounds and a lower bound for transformers
por: Madden, Liam, et al.
Publicado: (2024)

Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting
por: Shen, Tianqi, et al.
Publicado: (2026)

Koopman Lifted Finite Memory Identification via Truncated Grunwald Letnikov Kernels
por: Mojahed, Navid, et al.
Publicado: (2026)

Smooth Integer Encoding via Integral Balance
por: Semenov, Stanislav
Publicado: (2025)

A smoothing proximal gradient algorithm for matrix rank minimization problem
por: Yu, Quan, et al.
Publicado: (2021)

Using orthogonally structured positive bases for constructing positive $k$-spanning sets with cosine measure guarantees
por: Hare, Warren, et al.
Publicado: (2023)

On Bias and Its Reduction via Standardization in Discretized Electromagnetic Source Localization Problems
por: Lahtinen, Joonas
Publicado: (2024)

Comments and extensions on "State-equivalent form and minimum-order compensator design for rectangular descriptor systems"
por: Shi, Shuo, et al.
Publicado: (2025)

A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization
por: Chen, Po, et al.
Publicado: (2025)

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

Generic linear convergence for algorithms of non-linear least squares over smooth varieties
por: Hu, Shenglong, et al.
Publicado: (2025)

Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data
por: Fan, Chen, et al.
Publicado: (2025)

Implicit Bias and Fast Convergence Rates for Self-attention
por: Vasudeva, Bhavya, et al.
Publicado: (2024)

SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
por: Kranz, Julian, et al.
Publicado: (2025)

Efficient Defection: Overage-Proportional Rationing Attains the Cooperative Frontier
por: Lengyel, Florian
Publicado: (2025)

Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates
por: Esposito, Flavia, et al.
Publicado: (2025)

Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
por: Garrod, Connall, et al.
Publicado: (2025)

High-precision linear minimization is no slower than projection
por: Woodstock, Zev
Publicado: (2025)

Hautus-Type Criteria for Controllability and Stabilizability of Backward-Structured Stochastic Systems
por: Sun, Jingrui
Publicado: (2026)

Local minima in Newton's aerodynamical problem and inequalities between norms of partial derivatives
por: Plakhov, Alexander, et al.
Publicado: (2024)

Boundary Regional Controllability of Semilinear Systems Involving Caputo Time Fractional Derivatives
por: Tajani, Asmae, et al.
Publicado: (2024)

A Normal Map-Based Proximal Stochastic Gradient Method: Convergence and Identification Properties
por: Qiu, Junwen, et al.
Publicado: (2023)

A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization
por: Qiu, Junwen, et al.
Publicado: (2023)

Optimization without Retraction on the Random Generalized Stiefel Manifold
por: Vary, Simon, et al.
Publicado: (2024)

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

On semimonotone matrices of exact order two
por: Chauhan, Bharat Pratap, et al.
Publicado: (2026)

On the Characterization of gH-partial derivatives and gH-Product for Interval-Valued Functions
por: Suhail, Amir, et al.
Publicado: (2025)

On the Optimization and Generalization of Multi-head Attention
por: Deora, Puneesh, et al.
Publicado: (2023)

Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies
por: Roith, Tim, et al.
Publicado: (2025)

The Fundamental Theorem of Calculus in higher dimensions
por: Bár, Filip
Publicado: (2024)

Stiefel optimization is NP-hard
por: Lai, Zehua, et al.
Publicado: (2025)

A Large Deviations Perspective on Policy Gradient Algorithms
por: Jongeneel, Wouter, et al.
Publicado: (2023)

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
por: Barboni, Raphaël, et al.
Publicado: (2025)

Roots, trace, and extendability of flat nonnegative smooth functions
por: Jiang, Fushuai
Publicado: (2023)

On the controllability of nonlinear systems with a periodic drift
por: Caillau, Jean-Baptiste, et al.
Publicado: (2024)

Instability and Efficiency of Non-cooperative Games
por: Zhang, Jianfeng
Publicado: (2024)

Ultracoarse Equilibria and Ordinal-Folding Dynamics in Operator-Algebraic Models of Infinite Multi-Agent Games
por: Alpay, Faruk, et al.
Publicado: (2025)

FedSLoP: Memory-Efficient Federated Learning with Low-Rank Gradient Projection
por: He, Yutong, et al.
Publicado: (2026)

Monotonicity of the jump set and jump amplitudes in one-dimensional TV denoising
por: Cristoferi, Riccardo, et al.
Publicado: (2025)