No article text was recorded for this version.
single-step feature learning
Version 1 of 127 papers39 conceptsfrozen 2026-10-04
Papers in this version
- Blog: High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
- Blog: Grokking Beyond the Euclidean Norm of Model Parameters
- Blog: A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
- Blog: Asymptotics of feature learning in two-layer networks after one gradient-step
- Blog: Grokking as the transition from lazy to rich training dynamics
- Blog: Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
- Blog: Grokking modular arithmetic can be explained by margin maximization
- Blog: Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with Structure
- Blog: Language Models "Grok" to Copy
- Blog: Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory
- Blog: What Happens after SGD Reaches Zero Loss? --A Mathematical Framework
- Blog: Random Feature Amplification: Feature Learning and Generalization in Neural Networks
- Blog: Deep Orthogonal Representations: Fundamental Properties and Applications
- Blog: Neural representational geometries reflect behavioral differences in monkeys and recurrent neural networks
- Blog: Learning Parities with Neural Networks
- Blog: Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement
- Blog: Learning threshold neurons via edge of stability
- Blog: Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
- Blog: Provable Guarantees for Neural Networks via Gradient Feature Learning
- Blog: Disentangling feature and lazy learning in deep neural networks: an empirical study
- Blog: Analysing feature learning of gradient descent using periodic functions
- Blog: A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations
- Blog: Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
- Blog: Spectral Evolution and Invariance in Linear-width Neural Networks
- Blog: How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs
- Blog: Mathematical Models of Overparameterized Neural Networks
- Blog: Limitations of Lazy Training of Two-layers Neural Network
History & citation
Current · Permanent link
- Feature Learning with a Single Gradient Step merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_single_step_feature_learning_bc73bc28,
title = {single-step feature learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/single-step-feature-learning/rdr_bc73bc2825fb48e7b1bd774f499947ae},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_single_step_feature_learning_bc73bc28_v1,
title = {single-step feature learning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/single-step-feature-learning/rdr_bc73bc2825fb48e7b1bd774f499947ae/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}