Transformers perform kernel-based prediction for Hölder regression on manifolds and achieve intrinsic-dimension-dependent minimax rates with sufficient training tasks.
Provable in-context learning of linear systems and linear elliptic pdes with transformers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
CHOP reduces relative inference error on OOD operator tasks for scalar conservation laws and mean-field control by composing frozen ICON with explicit closed-form elementary operators that remain interpretable.
Transformers can be built to act as nonlinear featurizers via attention, supporting in-context regression with proven generalization bounds on synthetic tasks.
citing papers explorer
-
Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods
Transformers perform kernel-based prediction for Hölder regression on manifolds and achieve intrinsic-dimension-dependent minimax rates with sufficient training tasks.
-
Harness In-Context Operator Learning with Chain of Operators
CHOP reduces relative inference error on OOD operator tasks for scalar conservation laws and mean-field control by composing frozen ICON with explicit closed-form elementary operators that remain interpretable.
-
Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer
Transformers can be built to act as nonlinear featurizers via attention, supporting in-context regression with proven generalization bounds on synthetic tasks.