Adaptivity never hinders uniform approximation of task families but its advantages vary across four scenarios when moving from unrestricted to ReLU-realizable regimes.
L.How many pretraining tasks are needed for in-context learning of linear regression?arXiv preprint arXiv:2310.08391(2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning
Adaptivity never hinders uniform approximation of task families but its advantages vary across four scenarios when moving from unrestricted to ReLU-realizable regimes.