The gradient flow for linear in-context learning is derived in closed form, and two special cases are classified into attracting minima, saddle points, and invariant manifolds.
Can looped transformers learn to implement multi- step gradient descent for in-context learning? InProceedings of Interna- tional Conference on Machine Learning (ICML), 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
math.DS 1years
2024 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Dynamical Behaviors of the Gradient Flows for In-Context Learning
The gradient flow for linear in-context learning is derived in closed form, and two special cases are classified into attracting minima, saddle points, and invariant manifolds.