The paper claims a new family of embedding-based off-policy estimators for ranking policies, but its central unbiasedness theorem is false under the stated assumptions.
Note that for the RCV1-2K dataset, the top 1600 training and top 4000 test samples were extracted for the experiment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Off-Policy Evaluation of Ranking Policies via Embedding-Space User Behavior Modeling
The paper claims a new family of embedding-based off-policy estimators for ranking policies, but its central unbiasedness theorem is false under the stated assumptions.