Several fairness impossibility results share an RKHS geometry where linear mean constraints are overdetermined by unequal base rates, yielding the Pokémon theorem on residual MMD violations and feature-learning collapse.
Nikola Jovanovi´c, Mislav Balunovi ´c, Dimitar Iliev Dimitrov, and Martin Vechev
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Greedy linear models without exploration consistently achieve top-tier performance in over 90% of offline dataset evaluations for linear bandit recommenders, with hyperparameter tuning favoring minimal exploration and exposing biases in these protocols.
citing papers explorer
-
The Pok\'emon Theorem and other Fairness Impossibility Results
Several fairness impossibility results share an RKHS geometry where linear mean constraints are overdetermined by unequal base rates, yielding the Pokémon theorem on residual MMD violations and feature-learning collapse.
-
Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation
Greedy linear models without exploration consistently achieve top-tier performance in over 90% of offline dataset evaluations for linear bandit recommenders, with hyperparameter tuning favoring minimal exploration and exposing biases in these protocols.