Image de couverture de livre

The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Than, Khoat
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Using Synthetic Data to estimate the True Error is theoretically and practically doable
par: Thanh, Hai Hoang, et autres
Publié: (2025)

The Hidden Power of Pure 16-bit Floating-Point Neural Networks
par: Yun, Juyoung, et autres
Publié: (2023)

Gentle Local Robustness implies Generalization
par: Than, Khoat, et autres
Publié: (2024)

On the Nonlinearity of Layer Normalization
par: Ni, Yunhao, et autres
Publié: (2024)

LCA: Local Classifier Alignment for Continual Learning
par: Tran, Tung, et autres
Publié: (2026)

Compressing Neural Networks Using Tensor Networks with Exponentially Fewer Variational Parameters
par: Qing, Yong, et autres
Publié: (2023)

GRANOLA: Adaptive Normalization for Graph Neural Networks
par: Eliasof, Moshe, et autres
Publié: (2024)

DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks
par: Gülmez, Gökdeniz
Publié: (2026)

Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Compression of Deep Neural Networks
par: Cichocki, Andrzej, et autres
Publié: (2026)

LayerPipe2: Multistage Pipelining and Weight Recompute via Improved Exponential Moving Average for Training Neural Networks
par: Unnikrishnan, Nanda K., et autres
Publié: (2025)

Polysemanticity and Capacity in Neural Networks
par: Scherlis, Adam, et autres
Publié: (2022)

Separation Power of Equivariant Neural Networks
par: Pacini, Marco, et autres
Publié: (2024)

On the Expressive Power of Graph Neural Networks
par: Nalwade, Ashwin, et autres
Publié: (2024)

Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training
par: Chaudhary, Jatin, et autres
Publié: (2024)

Are Normalizing Flows the Key to Unlocking the Exponential Mechanism?
par: Bridges, Robert A., et autres
Publié: (2023)

Layer by Layer: Uncovering Hidden Representations in Language Models
par: Skean, Oscar, et autres
Publié: (2025)

Layer Embedding Deep Fusion Graph Neural Network
par: Xu, Taihua, et autres
Publié: (2026)

OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control Functions
par: Luo, Charles
Publié: (2026)

Symbol Correctness in Deep Neural Networks Containing Symbolic Layers
par: Bembenek, Aaron, et autres
Publié: (2024)

Exploring the Hidden Capacity of LLMs for One-Step Text Generation
par: Mezentsev, Gleb, et autres
Publié: (2025)

Empirical Capacity Model for Self-Attention Neural Networks
par: Härmä, Aki, et autres
Publié: (2024)

Provably Powerful Graph Neural Networks for Directed Multigraphs
par: Egressy, Béni, et autres
Publié: (2023)

Unveiling the Power of Sparse Neural Networks for Feature Selection
par: Atashgahi, Zahra, et autres
Publié: (2024)

Beyond Hidden-Layer Manipulation: Semantically-Aware Logit Interventions for Debiasing LLMs
par: Xia, Wei
Publié: (2025)

SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization
par: Song, Jaewoo, et autres
Publié: (2025)

SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints
par: Chu, Ya-Chi, et autres
Publié: (2026)

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension
par: Li, Jianfei, et autres
Publié: (2026)

Training-free Graph Neural Networks and the Power of Labels as Features
par: Sato, Ryoma
Publié: (2024)

EntroLnn: Entropy-Guided Liquid Neural Networks for Operando Refinement of Battery Capacity Fade Trajectories
par: Li, Wei, et autres
Publié: (2026)

Disentangling Neural Disjunctive Normal Form Models
par: Baugh, Kexin Gu, et autres
Publié: (2025)

SafePowerGraph: Safety-aware Evaluation of Graph Neural Networks for Transmission Power Grids
par: Ghamizi, Salah, et autres
Publié: (2024)

Stability of Transformers under Layer Normalization
par: Kan, Kelvin, et autres
Publié: (2025)

On the Weight Dynamics of Deep Normalized Networks
par: Mehmeti-Göpel, Christian H. X. Ali, et autres
Publié: (2023)

Towards Generalization of Graph Neural Networks for AC Optimal Power Flow
par: Arowolo, Olayiwola, et autres
Publié: (2025)

Müntz-Szász Networks: Neural Architectures with Learnable Power-Law Bases
par: N'guessan, Gnankan Landry Regis
Publié: (2025)

Climate Aware Deep Neural Networks (CADNN) for Wind Power Simulation
par: Forootani, Ali, et autres
Publié: (2024)

On the Role of Hidden States of Modern Hopfield Network in Transformer
par: Masumura, Tsubasa, et autres
Publié: (2025)

DeepDefense: Layer-Wise Gradient-Feature Alignment for Building Robust Neural Networks
par: Lin, Ci, et autres
Publié: (2025)

Imitation Learning Inputting Image Feature to Each Layer of Neural Network
par: Yamane, Koki, et autres
Publié: (2024)

Relative Layer-Wise Relevance Propagation: a more Robust Neural Networks eXplaination
par: Nyiri, Eric, et autres
Publié: (2025)