Deterministic preference feedback enables parametric distribution estimation at an O(1/n) rate, a quadratic improvement over the sample-only rate, with a matching minimax lower bound.
spiky” along some directions. Due to those distant vertices, the center would become a worse estimator than DP, since the “average
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Parametric Distributions from Samples and Preferences
Deterministic preference feedback enables parametric distribution estimation at an O(1/n) rate, a quadratic improvement over the sample-only rate, with a matching minimax lower bound.