Imagen de Portada

Depth Separations in Neural Networks: Separating the Dimension from the Accuracy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Safran, Itay, Reichman, Daniel, Valiant, Paul
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

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network
por: Dutta, Abhigyan, et al.
Publicado: (2026)

A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory
por: Safran, Itay
Publicado: (2026)

Provable Privacy Attacks on Trained Shallow Neural Networks
por: Smorodinsky, Guy, et al.
Publicado: (2024)

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
por: Smorodinsky, Guy, et al.
Publicado: (2026)

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks
por: Refael, Yehonatan, et al.
Publicado: (2025)

To Grok Grokking: Provable Grokking in Ridge Regression
por: Xu, Mingyue, et al.
Publicado: (2026)

Depth Separation in Norm-Bounded Infinite-Width Neural Networks
por: Parkinson, Suzanna, et al.
Publicado: (2024)

On the Depth of Monotone ReLU Neural Networks and ICNNs
por: Bakaev, Egor, et al.
Publicado: (2025)

Separable Hamiltonian Neural Networks
por: Khoo, Zi-Yu, et al.
Publicado: (2023)

Separation Power of Equivariant Neural Networks
por: Pacini, Marco, et al.
Publicado: (2024)

The Computational Complexity of Counting Linear Regions in ReLU Neural Networks
por: Stargalla, Moritz, et al.
Publicado: (2025)

Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics
por: Li, Yaojun, et al.
Publicado: (2026)

Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs
por: Yang, Qihong, et al.
Publicado: (2026)

In-Context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-Separation
por: Cole, Frank, et al.
Publicado: (2025)

Size and depth of monotone neural networks: interpolation and approximation
por: Mikulincer, Dan, et al.
Publicado: (2022)

Separable Operator Networks
por: Yu, Xinling, et al.
Publicado: (2024)

Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension
por: Xu, Alec S., et al.
Publicado: (2025)

Learning Traveling Solitary Waves Using Separable Gaussian Neural Networks
por: Xing, Siyuan, et al.
Publicado: (2024)

A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning
por: Jun, James P, et al.
Publicado: (2025)

Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks
por: Mattey, Revanth, et al.
Publicado: (2024)

On Cokriging, Neural Networks, and Spatial Blind Source Separation for Multivariate Spatial Prediction
por: Muehlmann, Christoph, et al.
Publicado: (2020)

Binaural Angular Separation Network
por: Yang, Yang, et al.
Publicado: (2024)

Separate Aggregation of Split Network for Personalized Federated Learning
por: Kang, Yunseok, et al.
Publicado: (2026)

Separated-Variable Spectral Neural Networks: A Physics-Informed Learning Approach for High-Frequency PDEs
por: Xiong, Xiong, et al.
Publicado: (2025)

Adaptive and oblivious statistical adversaries are equivalent
por: Blanc, Guy, et al.
Publicado: (2024)

Attainability of Two-Point Testing Rates for Finite-Sample Location Estimation
por: Compton, Spencer, et al.
Publicado: (2025)

Monotone and Separable Set Functions: Characterizations and Neural Models
por: Sarangi, Soutrik, et al.
Publicado: (2025)

Agile Reinforcement Learning through Separable Neural Architecture
por: Mostakim, Rajib, et al.
Publicado: (2026)

Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment
por: Haas, Nathanaël, et al.
Publicado: (2026)

The Implicit Bias of Gradient Descent on Separable Data
por: Soudry, Daniel, et al.
Publicado: (2017)

Estimating Dense-Packed Zone Height in Liquid-Liquid Separation: A Physics-Informed Neural Network Approach
por: Velioglu, Mehmet, et al.
Publicado: (2026)

The Implicit Bias of Gradient Descent on Separable Multiclass Data
por: Ravi, Hrithik, et al.
Publicado: (2024)

Comparative Separation: Evaluating Separation on Comparative Judgment Test Data
por: Xi, Xiaoyin, et al.
Publicado: (2026)

Solving Euler equations with Multiple Discontinuities via Separation-Transfer Physics-Informed Neural Networks
por: Wang, Chuanxing, et al.
Publicado: (2025)

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
por: Min, Hancheng, et al.
Publicado: (2025)

A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation
por: Watcharasupat, Karn N., et al.
Publicado: (2023)

Maximally Separated Active Learning
por: Kasarla, Tejaswi, et al.
Publicado: (2024)

Optimizing Neural Architectures for Hindi Speech Separation and Enhancement in Noisy Environments
por: Ramamoorthy, Arnav
Publicado: (2025)

SPIKANs: Separable Physics-Informed Kolmogorov-Arnold Networks
por: Jacob, Bruno, et al.
Publicado: (2024)

Quantization of Spiking Neural Networks Beyond Accuracy
por: Smith, Evan Gibson, et al.
Publicado: (2026)