GAIA models continuous utility with Gaussian processes across semantic space and applies fixed-share Hedge updates to achieve dynamic regret guarantees while outperforming baselines on three datasets.
Gomez, Adrien Morisot, Sebastian Farquhar, and Yarin Gal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Online Data Selection for Instruction Tuning via Gaussian Processes
GAIA models continuous utility with Gaussian processes across semantic space and applies fixed-share Hedge updates to achieve dynamic regret guarantees while outperforming baselines on three datasets.