Cover Image

Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking

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

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

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

Early-Warning Signals of Grokking via Loss-Landscape Geometry
by: Xu, Yongzhong
Published: (2026)

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

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

Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
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)

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

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
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)

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
by: Furuta, Hiroki, et al.
Published: (2024)

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

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

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

Grokking as a Variance-Limited Phase Transition: Spectral Gating and the Epsilon-Stability Threshold
by: Acharya, Pratyush, et al.
Published: (2026)

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

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent
by: Chou, Chi-Ning, et al.
Published: (2026)

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)

Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond
by: Jeffares, Alan, et al.
Published: (2024)

Grokking vs. Learning: Same Features, Different Encodings
by: Manning-Coe, Dmitry, et al.
Published: (2025)

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)

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

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

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)

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

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

Last Layer Empirical Bayes
by: Villecroze, Valentin, et al.
Published: (2025)

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

Grokking as a Falsifiable Finite-Size Transition
by: Bi, Yuda, et al.
Published: (2026)

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

Feature Identification via the Empirical NTK
by: Lin, Jennifer
Published: (2025)

Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport
by: Montesuma, Eduardo Fernandes, et al.
Published: (2025)

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