SAMO jointly uses global and local perturbations with forward-only task gradient approximation to improve multi-task learning performance at lower cost than F-MTL.
Sharpness-aware minimization leads to low-rank features
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
unclear 1representative citing papers
citing papers explorer
-
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation
SAMO jointly uses global and local perturbations with forward-only task gradient approximation to improve multi-task learning performance at lower cost than F-MTL.