Cover Image

Early-Warning Signals of Grokking via Loss-Landscape Geometry

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Xu, Yongzhong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure
by: Xu, Yongzhong
Published: (2026)

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking
by: Xu, Yongzhong
Published: (2026)

Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking
by: Xu, Yongzhong
Published: (2026)

Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
by: Xu, Yongzhong
Published: (2026)

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

Global Low-Rank, Local Full-Rank: The Holographic Encoding of Learned Algorithms
by: Xu, Yongzhong
Published: (2026)

Spectral Edge Dynamics Reveal Functional Modes of Learning
by: Xu, Yongzhong
Published: (2026)

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
by: Xu, Yongzhong
Published: (2026)

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers
by: Xu, Yongzhong
Published: (2026)

Spectral Edge Dynamics: An Analytical-Empirical Study of Phase Transitions in Neural Network Training
by: Xu, Yongzhong
Published: (2026)

When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures
by: Xu, Yongzhong
Published: (2026)

Optimizer-Induced Low-Dimensional Drift and Transverse Dynamics in Transformer Training
by: Xu, Yongzhong
Published: (2026)

Model Merging on Loss Landscape: A Geometry Perspective
by: Lu, Juanwu, et al.
Published: (2026)

Deep Learning for Disease Outbreak Prediction: A Robust Early Warning Signal for Transcritical Bifurcations
by: Miry, Reza, et al.
Published: (2025)

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
by: Lyu, Kaifeng, et al.
Published: (2023)

Topological Signatures of Grokking
by: Tang, Yifan, et al.
Published: (2026)

Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
by: Xu, Yongzhong
Published: (2026)

Early Warning of Intraoperative Adverse Events via Transformer-Driven Multi-Label Learning
by: Wang, Xueyao, et al.
Published: (2026)

Research on Early Warning Model of Cardiovascular Disease Based on Computer Deep Learning
by: Hu, Yuxiang, et al.
Published: (2024)

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

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

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

There is a Singularity in the Loss Landscape
by: Lowell, Mark
Published: (2022)

Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation
by: Park, Yeachan, et al.
Published: (2024)

Grokfast: Accelerated Grokking by Amplifying Slow Gradients
by: Lee, Jaerin, et al.
Published: (2024)

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

Progress Measures for Grokking on Real-world Tasks
by: Golechha, Satvik
Published: (2024)

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
by: Chen, Jiaqing, et al.
Published: (2026)

Anomaly Detection and Early Warning Mechanism for Intelligent Monitoring Systems in Multi-Cloud Environments Based on LLM
by: Jin, Yihong, et al.
Published: (2025)

Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
by: Salah, Ahmed, et al.
Published: (2025)

NeuralGrok: Accelerate Grokking by Neural Gradient Transformation
by: Zhou, Xinyu, et al.
Published: (2025)

Physics-Guided Tiny-Mamba Transformer for Reliability-Aware Early Fault Warning
by: Li, Changyu, et al.
Published: (2026)

An Attention-based Framework with Multistation Information for Earthquake Early Warnings
by: Huang, Yu-Ming, et al.
Published: (2024)

Visualizing Loss Functions as Topological Landscape Profiles
by: Geniesse, Caleb, et al.
Published: (2024)

Grokking Finite-Dimensional Algebra
by: Notsawo, Pascal Jr Tikeng, et al.
Published: (2026)

Grokking Group Multiplication with Cosets
by: Stander, Dashiell, et al.
Published: (2023)

Muon Optimizer Accelerates Grokking
by: Tveit, Amund, et al.
Published: (2025)

From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability
by: Hennick, Max, et al.
Published: (2026)

Learning Displacement-Robust Representations for Landslide Early Warning under Rainfall Forecast Uncertainty
by: Ozeki, Ren, et al.
Published: (2026)

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
by: Hidajat, Kai, et al.
Published: (2026)