NMT optimizes lower-priority tasks under a Lagrangian penalty that keeps the primary task loss near its pre-trained optimum, with no manual balancing weights in the loss combination.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods
NMT optimizes lower-priority tasks under a Lagrangian penalty that keeps the primary task loss near its pre-trained optimum, with no manual balancing weights in the loss combination.