Non-asymptotic analysis of prediction-powered mean estimation shows that no-regret learning for query probabilities converges to the maximum allowed constant value, independent of covariates.
Gaussian noiseϵ t ∼ N(0,10 −5)is added to eachx ⊤ t w∗ to produce the logits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Revisiting Active Sequential Prediction-Powered Mean Estimation
Non-asymptotic analysis of prediction-powered mean estimation shows that no-regret learning for query probabilities converges to the maximum allowed constant value, independent of covariates.