Cover Image

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chou, Chi-Ning, Uzdelewicz, Oscar, Chiu, Neng-Chun, Yang, Yao-Yuan, Chung, SueYeon
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

Linear Readout of Neural Manifolds with Continuous Variables
by: Slatton, Will, et al.
Published: (2026)

Diagnosing Generalization Failures from Representational Geometry Markers
by: Chou, Chi-Ning, et al.
Published: (2026)

Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
by: Chou, Chi-Ning, et al.
Published: (2025)

Nonlinear classification of neural manifolds with contextual information
by: Mignacco, Francesca, et al.
Published: (2024)

The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models
by: Kirsanov, Artem, et al.
Published: (2025)

Estimating Dimensionality of Neural Representations from Finite Samples
by: Chun, Chanwoo, et al.
Published: (2025)

Spectral Analysis of Representational Similarity with Limited Neurons
by: Kang, Hyunmo, et al.
Published: (2025)

Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
by: Halvagal, Manu Srinath, et al.
Published: (2026)

Emergent Manifold Separability during Reasoning in Large Language Models
by: Chun, Chanwoo, et al.
Published: (2026)

Statistical Mechanics of Support Vector Regression
by: Canatar, Abdulkadir, et al.
Published: (2024)

Estimating Neural Representation Alignment from Sparsely Sampled Inputs and Features
by: Chun, Chanwoo, et al.
Published: (2025)

Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices
by: Chun, Chanwoo, et al.
Published: (2024)

Neural population geometry and optimal coding of tasks with shared latent structure
by: Wakhloo, Albert J., et al.
Published: (2024)

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

On The Presence of Double-Descent in Deep Reinforcement Learning
by: Veselý, Viktor, et al.
Published: (2025)

Active Constraint Learning in High Dimensions from Demonstrations
by: Qiu, Zheng, et al.
Published: (2025)

Short‐Term Wind Speed Prediction Model Based on Hybrid Decomposition Method and Deep Learning
by: Xueqiong Yuan, et al.
Published: (2025)

On Double Descent in Reinforcement Learning with LSTD and Random Features
by: Brellmann, David, et al.
Published: (2023)

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

Grokking From Abstraction to Intelligence
by: Zhang, Junjie, et al.
Published: (2026)

Playstyle and Artificial Intelligence: An Initial Blueprint Through the Lens of Video Games
by: Lin, Chiu-Chou
Published: (2025)

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

CRISP: A Framework for Cryo-EM Image Segmentation and Processing with Conditional Random Field
by: Chung, Szu-Chi, 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)

Critical Data Size of Language Models from a Grokking Perspective
by: Zhu, Xuekai, et al.
Published: (2024)

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

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

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

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

Online Learning of Counter Categories and Ratings in PvP Games
by: Lin, Chiu-Chou, et al.
Published: (2025)

Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition
by: Huang, Yufei, et al.
Published: (2024)

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

Grokking at the Edge of Numerical Stability
by: Prieto, Lucas, 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)

Optimizing Low-Speed Autonomous Driving: A Reinforcement Learning Approach to Route Stability and Maximum Speed
by: Li, Benny Bao-Sheng, et al.
Published: (2024)

Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games
by: Lin, Chiu-Chou, et al.
Published: (2024)