An adaptive mixed-sample SGD procedure is claimed to converge at 1/sqrt(T) to a solution whose target risk matches the better of source-only and target-only ERM, but the main convergence bound contains a non-vanishing constant term, so the claim is not established.
Fast rates by transferring from auxiliary hypotheses
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer Learning
An adaptive mixed-sample SGD procedure is claimed to converge at 1/sqrt(T) to a solution whose target risk matches the better of source-only and target-only ERM, but the main convergence bound contains a non-vanishing constant term, so the claim is not established.