No article text was recorded for this version.
gradient descent equivalence
Version 1 of 116 papers24 conceptsfrozen 2026-10-04
Papers in this version
- Blog: One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
- Blog: How do Transformers Perform In-Context Autoregressive Learning ?
- Blog: Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
- Blog: On the Robustness of Transformers against Context Hijacking for Linear Classification
- Blog: Transformers Learn In-Context by Gradient Descent
- Blog: Transformers Learn In-Context by Gradient Descent
- Blog: On learning linear dynamical systems in context with attention layers
- Blog: Unraveling the Gradient Descent Dynamics of Transformers
- Blog: Max-Margin Token Selection in Attention Mechanism
- Blog: Graph Neural Networks Inspired by Classical Iterative Algorithms
- Blog: Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification
- Blog: The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
- Blog: From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
- Blog: Transformers are Minimax Optimal Nonparametric In-Context Learners
- Blog: Fine-grained Analysis of In-context Linear Estimation
- Blog: Transformers learn to implement preconditioned gradient descent for in-context learning
History & citation
Current · Permanent link
- This direction split from linear attention simplification (69% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gradient_descent_equivalence_1e3d9d9d,
title = {gradient descent equivalence},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-descent-equivalence/rdr_1e3d9d9db4764628be1700d4de9a0ff7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_gradient_descent_equivalence_1e3d9d9d_v1,
title = {gradient descent equivalence},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gradient-descent-equivalence/rdr_1e3d9d9db4764628be1700d4de9a0ff7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}