:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Miller, Jack, Gleeson, Patrick, O'Neill, Charles, Bui, Thang, Levi, Noam
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	https://arxiv.org/abs/2402.08946
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
par: O'Neill, Charles, et autres
Publié: (2024)

Grokking at the Edge of Linear Separability
par: Beck, Alon, et autres
Publié: (2024)

Self-Attention as a Parametric Endofunctor: A Categorical Framework for Transformer Architectures
par: O'Neill, Charles
Publié: (2025)

Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
par: Levi, Noam, et autres
Publié: (2023)

Type 2 Tobit Sample Selection Models with Bayesian Additive Regression Trees
par: O'Neill, Eoghan
Publié: (2025)

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
par: O'Neill, Charles, et autres
Publié: (2024)

Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders
par: O'Neill, Charles, et autres
Publié: (2025)

Likelihood approximations via Gaussian approximate inference
par: Bui, Thang D.
Publié: (2024)

A Simple Model of Inference Scaling Laws
par: Levi, Noam
Publié: (2024)

Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model
par: Levi, Noam
Publié: (2026)

Disentangling Dense Embeddings with Sparse Autoencoders
par: O'Neill, Charles, et autres
Publié: (2024)

Sketching the Heat Kernel: Using Gaussian Processes to Embed Data
par: Gilbert, Anna C., et autres
Publié: (2024)

Beyond ReinMax: Low-Variance Gradient Estimators for Discrete Latent Variables
par: Wang, Daniel, et autres
Publié: (2026)

Modelling the Doughnut of social and planetary boundaries with frugal machine learning
par: Vrizzi, Stefano, et autres
Publié: (2025)

From superposition to sparse codes: interpretable representations in neural networks
par: Klindt, David, et autres
Publié: (2025)

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

Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking
par: Gu, Zihan, et autres
Publié: (2025)

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

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
par: O'Neill, Charles, et autres
Publié: (2025)

Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited
par: Bui, Thang D., et autres
Publié: (2025)

CA-PCA: Manifold Dimension Estimation, Adapted for Curvature
par: Gilbert, Anna C., et autres
Publié: (2023)

Low-Rank Key Value Attention
par: O'Neill, James, et autres
Publié: (2026)

The Complexity Dynamics of Grokking
par: DeMoss, Branton, et autres
Publié: (2024)

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

The Implicit Bias of Logit Regularization
par: Beck, Alon, et autres
Publié: (2026)

Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
par: Cohen, Khen, et autres
Publié: (2024)

Late-Stage Generalization Collapse in Grokking: Detecting anti-grokking with Weightwatcher
par: Prakash, Hari K, et autres
Publié: (2026)

The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets
par: Levi, Noam, et autres
Publié: (2023)

Grokking and Generalization Collapse: Insights from \texttt{HTSR} theory
par: Prakash, Hari K., et autres
Publié: (2025)

Tighter sparse variational Gaussian processes
par: Bui, Thang D., et autres
Publié: (2025)

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

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

Information-Theoretic Progress Measures reveal Grokking is an Emergent Phase Transition
par: Clauw, Kenzo, et autres
Publié: (2024)

Pretraining Scaling Laws for Generative Evaluations of Language Models
par: Schaeffer, Rylan, et autres
Publié: (2025)

Decoupled Weight Decay for Any $p$ Norm
par: Outmezguine, Nadav Joseph, et autres
Publié: (2024)

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

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