Pith. sign in

Making better use of unlabelled data in Bayesian active learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2024 1

verdicts

ACCEPT 1

representative citing papers

Rethinking Aleatoric and Epistemic Uncertainty

cs.LG · 2024-12-30 · accept · novelty 7.0

Uncertainty, predictive performance, and data dispersion can be cleanly separated through a decision-theoretic lens, and BALD is best seen as an estimator of short-run parameter information gain rather than a direct measure of reducible predictive uncertainty.

citing papers explorer

Showing 1 of 1 citing paper.

  • Rethinking Aleatoric and Epistemic Uncertainty cs.LG · 2024-12-30 · accept · none · ref 7

    Uncertainty, predictive performance, and data dispersion can be cleanly separated through a decision-theoretic lens, and BALD is best seen as an estimator of short-run parameter information gain rather than a direct measure of reducible predictive uncertainty.