Argo achieves 148-167X lower inference cost for email importance labeling with negligible quality loss by searching cost-quality trade-offs and using on-demand scaling across three open-source datasets.
Normalized wasser- stein distance for mixture distributions with applications in adversarial learning and domain adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Argo: Efficient Importance Labeling for Enterprise Email Systems
Argo achieves 148-167X lower inference cost for email importance labeling with negligible quality loss by searching cost-quality trade-offs and using on-demand scaling across three open-source datasets.