Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Khanh, Truong Xuan, Hoa, Truong Quynh
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

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

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

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization
di: Khanh, Truong Xuan, et al.
Pubblicazione: (2026)

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

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

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

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

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

Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning
di: Rodriguez-Alvarez, Nicolas, et al.
Pubblicazione: (2026)

Why Do Safety Guardrails Degrade Across Languages?
di: Zhang, Max, et al.
Pubblicazione: (2026)

Large-Scale Multipurpose Benchmark Datasets For Assessing Data-Driven Deep Learning Approaches For Water Distribution Networks
di: Tello, Andres, et al.
Pubblicazione: (2024)

Hierarchy Representation of Data in Machine Learnings
di: Yegang, Han, et al.
Pubblicazione: (2023)

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

Efficient Modular Learning through Naive LoRA Summation: Leveraging Orthogonality in High-Dimensional Models
di: Cao, Zhanhao, et al.
Pubblicazione: (2025)

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

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

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

DiTEC-WDN: A Large-Scale Dataset of Hydraulic Scenarios across Multiple Water Distribution Networks
di: Truong, Huy, et al.
Pubblicazione: (2025)

Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More
di: Lim, Jinwoo, et al.
Pubblicazione: (2026)

Graph Neural Networks for Learning Equivariant Representations of Neural Networks
di: Kofinas, Miltiadis, et al.
Pubblicazione: (2024)

Mitigating Shortcut Learning with InterpoLated Learning
di: Korakakis, Michalis, et al.
Pubblicazione: (2025)

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
di: Jiang, Fengqing, et al.
Pubblicazione: (2026)

Learning with Logical Constraints but without Shortcut Satisfaction
di: Li, Zenan, et al.
Pubblicazione: (2024)

Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds
di: Chen, Edward, et al.
Pubblicazione: (2025)

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
di: Cao, Yuan-dong, et al.
Pubblicazione: (2026)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
di: Zhu, Yunqin, et al.
Pubblicazione: (2026)

Physics-inspired Energy Transition Neural Network for Sequence Learning
di: Wu, Zhou, et al.
Pubblicazione: (2025)

Rectifying Shortcut Behaviors in Preference-based Reward Learning
di: Ye, Wenqian, et al.
Pubblicazione: (2025)

Transformers Learn Robust In-Context Regression under Distributional Uncertainty
di: Cao, Hoang T. H., et al.
Pubblicazione: (2026)

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

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
di: Tang, Xuan, et al.
Pubblicazione: (2025)

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

Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies
di: Piękos, Piotr, et al.
Pubblicazione: (2025)

Stronger Enforcement of Instruction Hierarchy via Augmented Intermediate Representations
di: Kariyappa, Sanjay, et al.
Pubblicazione: (2025)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
di: Wang, Xiangmeng, et al.
Pubblicazione: (2026)

MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
di: Zhao, Lili, et al.
Pubblicazione: (2025)

Revisiting LARS for Large Batch Training Generalization of Neural Networks
di: Do, Khoi, et al.
Pubblicazione: (2023)

Graph Neural Networks Use Graphs When They Shouldn't
di: Bechler-Speicher, Maya, et al.
Pubblicazione: (2023)

Learning Label Hierarchy with Supervised Contrastive Learning
di: Lian, Ruixue, et al.
Pubblicazione: (2024)

Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship
di: Nguyen, Nang Hung, et al.
Pubblicazione: (2026)