Training-order effects in multi-domain learning are governed by the Lie bracket of the per-domain gradient flows, yielding a local optimality criterion for weight schedules.
Order matters in the presence of dataset imbalance for multilingual learning
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
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
Training-order effects in multi-domain learning are governed by the Lie bracket of the per-domain gradient flows, yielding a local optimality criterion for weight schedules.