The work establishes a regret lower bound of Ω(T^{2/3} min(K,D)^{1/3}) for fair multi-user dueling bandits with heterogeneous Condorcet winners and gives algorithms achieving matching upper bounds up to logs.
Proceedings of the 3rd innovations in theoretical computer science conference , pages=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
CDSP uses an effect-size asymmetry assumption and statistical power to estimate causal directions from bivariate data with uncertainty, reducing false discoveries by 18% on 100 benchmark pairs.
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
citing papers explorer
-
Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare
The work establishes a regret lower bound of Ω(T^{2/3} min(K,D)^{1/3}) for fair multi-user dueling bandits with heterogeneous Condorcet winners and gives algorithms achieving matching upper bounds up to logs.
-
Causal Discovery via Statistical Power (CDSP)
CDSP uses an effect-size asymmetry assumption and statistical power to estimate causal directions from bivariate data with uncertainty, reducing false discoveries by 18% on 100 benchmark pairs.
-
Explainable AI Isn't Enough! Rethinking Algorithmic Contestability
The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.
- Assessing Predictive Models for Fairness Based on Movement Patterns
- Check, Please: Verifiably Fair Clustering
- Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution