Image de couverture de livre

A Stable Whitening Optimizer for Efficient Neural Network Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Frans, Kevin, Levine, Sergey, Abbeel, Pieter
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

What Really Matters in Matrix-Whitening Optimizers?
par: Frans, Kevin, et autres
Publié: (2025)

Diffusion Guidance Is a Controllable Policy Improvement Operator
par: Frans, Kevin, et autres
Publié: (2025)

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings
par: Frans, Kevin, et autres
Publié: (2024)

One Step Diffusion via Shortcut Models
par: Frans, Kevin, et autres
Publié: (2024)

Prioritized Generative Replay
par: Wang, Renhao, et autres
Publié: (2024)

Cliqueformer: Model-Based Optimization with Structured Transformers
par: Kuba, Jakub Grudzien, et autres
Publié: (2024)

Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
par: Kuba, Jakub Grudzien, et autres
Publié: (2024)

Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration
par: Wilcoxson, Max, et autres
Publié: (2024)

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
par: Seo, Younggyo, et autres
Publié: (2024)

Is Value Learning Really the Main Bottleneck in Offline RL?
par: Park, Seohong, et autres
Publié: (2024)

OGBench: Benchmarking Offline Goal-Conditioned RL
par: Park, Seohong, et autres
Publié: (2024)

Compute-Optimal Scaling for Value-Based Deep RL
par: Fu, Preston, et autres
Publié: (2025)

Value-Based Deep RL Scales Predictably
par: Rybkin, Oleh, et autres
Publié: (2025)

SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation
par: Lee, Jongmin, et autres
Publié: (2025)

Reward-Conditioned Reinforcement Learning
par: Nauman, Michal, et autres
Publié: (2026)

Deep Neural Networks Tend To Extrapolate Predictably
par: Kang, Katie, et autres
Publié: (2023)

Horizon Reduction Makes RL Scalable
par: Park, Seohong, et autres
Publié: (2025)

Depth-Aware Initialization for Stable and Efficient Neural Network Training
par: Pandey, Vijay
Publié: (2025)

Offline Imitation Learning Through Graph Search and Retrieval
par: Yin, Zhao-Heng, et autres
Publié: (2024)

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
par: Nauman, Michal, et autres
Publié: (2025)

Zipfian Whitening
par: Yokoi, Sho, et autres
Publié: (2024)

Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
par: Revin, Ilia, et autres
Publié: (2025)

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
par: Lee, Vint, et autres
Publié: (2023)

World Model on Million-Length Video And Language With Blockwise RingAttention
par: Liu, Hao, et autres
Publié: (2024)

Visual Pre-Training on Unlabeled Images using Reinforcement Learning
par: Ghosh, Dibya, et autres
Publié: (2025)

SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
par: Ma, Chao, et autres
Publié: (2024)

Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
par: Rachmil, Oren, et autres
Publié: (2025)

A Training Framework for Optimal and Stable Training of Polynomial Neural Networks
par: Hossain, Forsad Al, et autres
Publié: (2025)

Cross-Entropy Optimization for Hyperparameter Optimization in Stochastic Gradient-based Approaches to Train Deep Neural Networks
par: Li, Kevin, et autres
Publié: (2024)

Learning a Diffusion Model Policy from Rewards via Q-Score Matching
par: Psenka, Michael, et autres
Publié: (2023)

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
par: Kim, Dongyoung, et autres
Publié: (2023)

ViVa: Video-Trained Value Functions for Guiding Online RL from Diverse Data
par: Dashora, Nitish, et autres
Publié: (2025)

Training Diffusion Models with Reinforcement Learning
par: Black, Kevin, et autres
Publié: (2023)

Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction
par: Jang, Huiwon, et autres
Publié: (2024)

Understanding SOAP from the Perspective of Gradient Whitening
par: Lu, Yanqing, et autres
Publié: (2025)

Training Neural Networks by Optimizing Neuron Positions
par: Erb, Laura, et autres
Publié: (2025)

Real-Time Execution of Action Chunking Flow Policies
par: Black, Kevin, et autres
Publié: (2025)

Whitening Spherical Gaussian Mixtures in the Large-Dimensional Regime
par: Boudjemaa, Mohammed Racim Moussa, et autres
Publié: (2025)

Contextual Bandit Optimization with Pre-Trained Neural Networks
par: Terekhov, Mikhail
Publié: (2025)

UnifiedNN: Efficient Neural Network Training on the Cloud
par: Taki, Sifat Ut, et autres
Publié: (2024)