Copertina

StableGrad: Backward Scale Control without Batch Normalization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mestre, Jose I., Fernández-Hernández, Alberto, Pérez-Corral, Cristian, Dolz, Manuel F., Quintana-Ortí, Enrique S.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Why Adam Works Better with $β_1 = β_2$: The Missing Gradient Scale Invariance Principle
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2026)

$λ$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
di: Pérez-Corral, Cristian, et al.
Pubblicazione: (2026)

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2026)

GLAI: GreenLightningAI for Accelerated Training through Knowledge Decoupling
di: Mestre, Jose I., et al.
Pubblicazione: (2025)

Refresh-Scaling the Memory of Balanced Adam
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2026)

Regime Change Hypothesis: Foundations for Decoupled Dynamics in Neural Network Training
di: Pérez-Corral, Cristian, et al.
Pubblicazione: (2026)

FedSQ: Optimized Weight Averaging via Fixed Gating
di: Pérez-Corral, Cristian, et al.
Pubblicazione: (2026)

Detecting Atypical Clients in Federated Learning via Representation-Level Divergence
di: Pérez-Corral, Cristian, et al.
Pubblicazione: (2026)

OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2025)

Sinusoidal Initialization, Time for a New Start
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2025)

OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2026)

FedOUI: OUI-Guided Client Weighting for Federated Aggregation
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2026)

OUI as a Structural Observable: Towards an Activation-Centric View of Neural Network Training
di: Fernández-Hernández, Alberto, et al.
Pubblicazione: (2026)

Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
di: Palenicek, Daniel, et al.
Pubblicazione: (2025)

AlphaGrad: Non-Linear Gradient Normalization Optimizer
di: Sane, Soham
Pubblicazione: (2025)

Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework
di: Wang, Shaobo, et al.
Pubblicazione: (2023)

Mapping Parallel Matrix Multiplication in GotoBLAS2 to the AMD Versal ACAP for Deep Learning
di: Lei, Jie, et al.
Pubblicazione: (2024)

Batch Normalization Amplifies Memorization and Privacy Risks
di: Doan, Ngoc Phu, et al.
Pubblicazione: (2026)

Riemannian Batch Normalization: A Gyro Approach
di: Chen, Ziheng, et al.
Pubblicazione: (2025)

From domain-landmark graph learning to problem-landmark graph generation
di: Pérez-Corral, Cristian, et al.
Pubblicazione: (2025)

Performance Analysis of Matrix Multiplication for Deep Learning on the Edge
di: Ramírez, Cristian, et al.
Pubblicazione: (2024)

Making Batch Normalization Great in Federated Deep Learning
di: Zhong, Jike, et al.
Pubblicazione: (2023)

A Lie Group Approach to Riemannian Batch Normalization
di: Chen, Ziheng, et al.
Pubblicazione: (2024)

Exploring Batch Normalization’s Impact on Dense Layers of Multiclass and Multilabel Classifiers
di: Misganaw Aguate Widneh, et al.
Pubblicazione: (2025)

Transformers without Normalization
di: Zhu, Jiachen, et al.
Pubblicazione: (2025)

StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
di: Ye, Chongjie, et al.
Pubblicazione: (2024)

How to Set the Batch Size for Large-Scale Pre-training?
di: Zhou, Yunhua, et al.
Pubblicazione: (2026)

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
di: Choudhury, Sayantan, et al.
Pubblicazione: (2024)

AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size
di: Ostroukhov, Petr, et al.
Pubblicazione: (2024)

Thinking Forward and Backward: Effective Backward Planning with Large Language Models
di: Ren, Allen Z., et al.
Pubblicazione: (2024)

NERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation
di: Mahatha, Kunal, et al.
Pubblicazione: (2025)

Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling
di: Park, Jongchan
Pubblicazione: (2026)

GradINN: Gradient Informed Neural Network
di: Aglietti, Filippo, et al.
Pubblicazione: (2024)

Fast Truncated SVD of Sparse and Dense Matrices on Graphics Processors
di: Tomas, Andres E., et al.
Pubblicazione: (2024)

Iterative Learning Control-Informed Reinforcement Learning for Batch Process Control
di: Lin, Runze, et al.
Pubblicazione: (2026)

On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
di: Armengol-Estapé, Jordi, et al.
Pubblicazione: (2024)

MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization
di: Fei, Wen, et al.
Pubblicazione: (2020)

Implementing Basic Arithmetic in $\mathbb{F}_p$ via $\mathbb{F}_2$, and Its Application for Computing the Hamming Distance of Linear Codes
di: Hernando, Fernando, et al.
Pubblicazione: (2026)

Neural Networks With Linear Adaptive Batch Normalization and Swarm Intelligence Calibration for Real‐Time Gaze Estimation on Smartphones
di: Gancheng Zhu, et al.
Pubblicazione: (2024)

GradMetaNet: An Equivariant Architecture for Learning on Gradients
di: Gelberg, Yoav, et al.
Pubblicazione: (2025)