Under explicit injectivity and smoothness assumptions, grouped language probabilities can be inverted into state posteriors, with nonparametric rates, partial-identification sets, and a minimax limit on stability certification.
Ramon van Handel
1 Pith paper cite this work, alongside 40 external citations. Polarity classification is still indexing.
1
Pith paper citing it
40
external citations · OpenAlex
fields
stat.ME 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identification and Learning of Semantic Observation Kernels: Partial Observation, Uniform Recovery, & Minimax Limits
Under explicit injectivity and smoothness assumptions, grouped language probabilities can be inverted into state posteriors, with nonparametric rates, partial-identification sets, and a minimax limit on stability certification.