Image de couverture de livre

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Khanh, Truong Xuan, Hoa, Truong Quynh
Format:	Preprint
Publié:	2026
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

Intelligence as Trajectory-Dominant Pareto Optimization
par: Khanh, Truong Xuan, et autres
Publié: (2026)

Dynamic Intelligence Ceilings: Measuring Long-Horizon Limits of Planning and Creativity in Artificial Systems
par: Khanh, Truong Xuan, et autres
Publié: (2026)

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization
par: Khanh, Truong Xuan, et autres
Publié: (2026)

Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
par: Hoa, Truong Quynh, et autres
Publié: (2026)

Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin
par: Khanh, Truong Xuan, et autres
Publié: (2026)

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

First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
par: Khanh, Truong Xuan, et autres
Publié: (2026)

Entropy Collapse: A Universal Failure Mode of Intelligent Systems
par: Khanh, Truong Xuan, et autres
Publié: (2025)

Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning
par: Rodriguez-Alvarez, Nicolas, et autres
Publié: (2026)

Why Do Safety Guardrails Degrade Across Languages?
par: Zhang, Max, et autres
Publié: (2026)

Large-Scale Multipurpose Benchmark Datasets For Assessing Data-Driven Deep Learning Approaches For Water Distribution Networks
par: Tello, Andres, et autres
Publié: (2024)

Hierarchy Representation of Data in Machine Learnings
par: Yegang, Han, et autres
Publié: (2023)

Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
par: Nguyen, Tien-Phat, et autres
Publié: (2026)

Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models
par: Cao, Zhanhao, et autres
Publié: (2025)

Solving Cyclic Antibandwidth Problem by SAT
par: Xuan, Hieu Truong, et autres
Publié: (2026)

SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization
par: Quan, Xuan-Truong, et autres
Publié: (2025)

Amortized Optimal Transport from Sliced Potentials
par: Truong, Minh-Phuc, et autres
Publié: (2026)

DiTEC-WDN: A Large-Scale Dataset of Hydraulic Scenarios across Multiple Water Distribution Networks
par: Truong, Huy, et autres
Publié: (2025)

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
par: Lim, Jinwoo, et autres
Publié: (2026)

Graph Neural Networks for Learning Equivariant Representations of Neural Networks
par: Kofinas, Miltiadis, et autres
Publié: (2024)

Mitigating Shortcut Learning with InterpoLated Learning
par: Korakakis, Michalis, et autres
Publié: (2025)

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
par: Jiang, Fengqing, et autres
Publié: (2026)

Learning with Logical Constraints but without Shortcut Satisfaction
par: Li, Zenan, et autres
Publié: (2024)

Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds
par: Chen, Edward, et autres
Publié: (2025)

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
par: Cao, Yuan-dong, et autres
Publié: (2026)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
par: Zhu, Yunqin, et autres
Publié: (2026)

Physics-inspired Energy Transition Neural Network for Sequence Learning
par: Wu, Zhou, et autres
Publié: (2025)

Rectifying Shortcut Behaviors in Preference-based Reward Learning
par: Ye, Wenqian, et autres
Publié: (2025)

Transformers Learn Robust In-Context Regression under Distributional Uncertainty
par: Cao, Hoang T. H., et autres
Publié: (2026)

XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach
par: Nguyen, Truong Thanh Hung, et autres
Publié: (2024)

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
par: Tang, Xuan, et autres
Publié: (2025)

Neural Nonmyopic Bayesian Optimization in Dynamic Cost Settings
par: Truong, Sang T., et autres
Publié: (2026)

Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies
par: Piękos, Piotr, et autres
Publié: (2025)

Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations
par: Kariyappa, Sanjay, et autres
Publié: (2025)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
par: Wang, Xiangmeng, et autres
Publié: (2026)

MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
par: Zhao, Lili, et autres
Publié: (2025)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
par: Do, Khoi, et autres
Publié: (2023)

Graph Neural Networks Use Graphs When They Shouldn't
par: Bechler-Speicher, Maya, et autres
Publié: (2023)

Learning Label Hierarchy with Supervised Contrastive Learning
par: Lian, Ruixue, et autres
Publié: (2024)

Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship
par: Nguyen, Nang Hung, et autres
Publié: (2026)