Imagen de Portada

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Khanh, Truong Xuan, Hoa, Truong Quynh, Trung, Luu Duc, Duc, Phan Thanh
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

Intelligence as Trajectory-Dominant Pareto Optimization
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
por: Hoa, Truong Quynh, et al.
Publicado: (2026)

Entropy Collapse: A Universal Failure Mode of Intelligent Systems
por: Khanh, Truong Xuan, et al.
Publicado: (2025)

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
por: Khanh, Truong Xuan
Publicado: (2026)

SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization
por: Quan, Xuan-Truong, et al.
Publicado: (2025)

RobustFSM: Submodular Maximization in Federated Setting with Malicious Clients
por: Tran, Duc A., et al.
Publicado: (2025)

The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
por: Musat, Tiberiu
Publicado: (2025)

BOLIMES: Boruta and LIME optiMized fEature Selection for Gene Expression Classification
por: Phan, Bich-Chung, et al.
Publicado: (2025)

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
por: Nguyen, Tien-Phat, et al.
Publicado: (2026)

Grokking Beyond the Euclidean Norm of Model Parameters
por: Notsawo, Pascal Jr Tikeng, et al.
Publicado: (2025)

CryoSAMU: Enhancing 3D Cryo-EM Density Maps of Protein Structures at Intermediate Resolution with Structure-Aware Multimodal U-Nets
por: Zhang, Chenwei, et al.
Publicado: (2025)

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
por: Phan, Hoang, et al.
Publicado: (2022)

R.I.P.: A Simple Black-box Attack on Continual Test-time Adaptation
por: Hoang, Trung-Hieu, et al.
Publicado: (2024)

XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach
por: Nguyen, Truong Thanh Hung, et al.
Publicado: (2024)

Enhancing Time Series Forecasting via a Parallel Hybridization of ARIMA and Polynomial Classifiers
por: Nguyen, Thanh Son, et al.
Publicado: (2025)

Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking
por: Tian, Yuandong
Publicado: (2025)

BSO: Safety Alignment Is Density Ratio Matching
por: Nguyen, Tien-Phat, et al.
Publicado: (2026)

Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings
por: Truong, Sang T., et al.
Publicado: (2026)

DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays
por: Xia, Bo, et al.
Publicado: (2024)

A Pre-training Framework for Relational Data with Information-theoretic Principles
por: Truong, Quang, et al.
Publicado: (2025)

Audio-3DVG: Unified Audio -- Point Cloud Fusion for 3D Visual Grounding
por: Cao-Dinh, Duc, et al.
Publicado: (2025)

Empowering Contrastive Federated Sequential Recommendation with LLMs
por: Nguyen, Thi Minh Chau, et al.
Publicado: (2026)

Topological Signatures of Grokking
por: Tang, Yifan, et al.
Publicado: (2026)

Solving Cyclic Antibandwidth Problem by SAT
por: Xuan, Hieu Truong, et al.
Publicado: (2026)

Grokking Explained: A Statistical Phenomenon
por: Carvalho, Breno W., et al.
Publicado: (2025)

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling
por: Tran, Dao, et al.
Publicado: (2026)

Sentiment Reasoning for Healthcare
por: Nguyen, Khai-Nguyen, et al.
Publicado: (2024)

Amortized Optimal Transport from Sliced Potentials
por: Truong, Minh-Phuc, et al.
Publicado: (2026)

Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory
por: Prakash, Hari K., et al.
Publicado: (2025)

Variational Delayed Policy Optimization
por: Wu, Qingyuan, et al.
Publicado: (2024)

Understanding Grokking Through A Robustness Viewpoint
por: Tan, Zhiquan, et al.
Publicado: (2023)

Real-time Speech Summarization for Medical Conversations
por: Le-Duc, Khai, et al.
Publicado: (2024)

RAISE: A Unified Framework for Responsible AI Scoring and Evaluation
por: Nguyen, Loc Phuc Truong, et al.
Publicado: (2025)

BRIDGE: Bundle Recommendation via Instruction-Driven Generation
por: Bui, Tuan-Nghia, et al.
Publicado: (2024)

Grokking in Linear Models for Logistic Regression
por: Das, Nataraj, et al.
Publicado: (2026)

Controlling Grokking with Nonlinearity and Data Symmetry
por: Salah, Ahmed, et al.
Publicado: (2024)