Image de couverture de livre

The Complexity Dynamics of Grokking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	DeMoss, Branton, Sapora, Silvia, Foerster, Jakob, Hawes, Nick, Posner, Ingmar
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DITTO: Offline Imitation Learning with World Models
par: DeMoss, Branton, et autres
Publié: (2023)

LUMOS: Language-Conditioned Imitation Learning with World Models
par: Nematollahi, Iman, et autres
Publié: (2025)

Improving Regret Approximation for Unsupervised Dynamic Environment Generation
par: Mead, Harry, et autres
Publié: (2026)

Meta-Learning Objectives for Preference Optimization
par: Alfano, Carlo, et autres
Publié: (2024)

EvIL: Evolution Strategies for Generalisable Imitation Learning
par: Sapora, Silvia, et autres
Publié: (2024)

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
par: Cook, Jonathan, et autres
Publié: (2025)

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
par: Rutherford, Alexander, et autres
Publié: (2024)

SPARTAN: A Sparse Transformer World Model Attending to What Matters
par: Lei, Anson, et autres
Publié: (2024)

Reward-Free Curricula for Training Robust World Models
par: Rigter, Marc, et autres
Publié: (2023)

Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attention
par: Baumgartner, Markus W., et autres
Publié: (2026)

Entropic Riemannian Neural Optimal Transport
par: Micheli, Alessandro, et autres
Publié: (2026)

World Models via Policy-Guided Trajectory Diffusion
par: Rigter, Marc, et autres
Publié: (2023)

Compete and Compose: Learning Independent Mechanisms for Modular World Models
par: Lei, Anson, et autres
Publié: (2024)

Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
par: Flynn, Hamish, et autres
Publié: (2026)

To Grok Grokking: Provable Grokking in Ridge Regression
par: Xu, Mingyue, et autres
Publié: (2026)

D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation
par: Yamada, Jun, et autres
Publié: (2024)

Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
par: Miller, Jack, et autres
Publié: (2023)

Learning mirror maps in policy mirror descent
par: Alfano, Carlo, et autres
Publié: (2024)

GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning
par: Sapora, Silvia, et autres
Publié: (2025)

COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping
par: Yamada, Jun, et autres
Publié: (2025)

Measuring Sharpness in Grokking
par: Miller, Jack, et autres
Publié: (2024)

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
par: Minegishi, Gouki, et autres
Publié: (2023)

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

Grokked Models are Better Unlearners
par: Liang, Yuanbang, et autres
Publié: (2025)

XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
par: Palenicek, Daniel, et autres
Publié: (2025)

Topological Signatures of Grokking
par: Tang, Yifan, et autres
Publié: (2026)

Gaitor: Learning a Unified Representation Across Gaits for Real-World Quadruped Locomotion
par: Mitchell, Alexander L., et autres
Publié: (2024)

JaxUED: A simple and useable UED library in Jax
par: Coward, Samuel, et autres
Publié: (2024)

XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies
par: Palenicek, Daniel, et autres
Publié: (2026)

Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
par: Scherer, Christian, et autres
Publié: (2026)

Exploring Grokking: Experimental and Mechanistic Investigations
par: Qiye, Hu, et autres
Publié: (2024)

ILDR: Geometric Early Detection of Grokking
par: Golwala, Shreel
Publié: (2026)

Monte Carlo Tree Search with Boltzmann Exploration
par: Painter, Michael, et autres
Publié: (2024)

Return Capping: Sample-Efficient CVaR Policy Gradient Optimisation
par: Mead, Harry, et autres
Publié: (2025)

Grokking as the Transition from Lazy to Rich Training Dynamics
par: Kumar, Tanishq, et autres
Publié: (2023)

Intrinsically Interpretable Attention via Sparse Post-Training
par: Draye, Florent, et autres
Publié: (2025)

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

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
par: He, Jianliang, et autres
Publié: (2026)

Distributional Spectral Diagnostics for Localizing Grokking Transitions
par: Wang, Ziyue, et autres
Publié: (2026)

GrokAlign: Geometric Characterisation and Acceleration of Grokking
par: Walker, Thomas, et autres
Publié: (2025)