Search Results for author:
Found 9 papers, 1 papers with code
Calibration for the (Computationally-Identifiable) Masses
We develop and study multicalbration -- a new measure of algorithmic fairness that aims to mitigate concerns about discrimination that is introduced in the process of learning a predictor from data.
Fairness Through Computationally-Bounded Awareness
We study the problem of fair classification within the versatile framework of Dwork et al. [ITCS '12], which assumes the existence of a metric that measures similarity between pairs of individuals.
Probably Approximately Metric-Fair Learning
We show that approximate metric-fairness {\em does} generalize, and leverage these generalization guarantees to construct polynomial-time PACF learning algorithms for the classes of linear and logistic predictors.
Preference-Informed Fairness
We introduce and study a new notion of preference-informed individual fairness (PIIF) that is a relaxation of both individual fairness and envy-freeness.
Abstracting Fairness: Oracles, Metrics, and Interpretability
Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle.
Outcome Indistinguishability
Prediction algorithms assign numbers to individuals that are popularly understood as individual "probabilities" -- what is the probability of 5-year survival after cancer diagnosis?
Consider the Alternatives: Navigating Fairness-Accuracy Tradeoffs via Disqualification
The notion of "too much" is quantified via a parameter $\gamma$ that serves as a vehicle for specifying acceptable tradeoffs between accuracy and fairness, in a way that is independent from the specific metrics used to quantify fairness and accuracy in a given task.
Decision-Making under Miscalibration
We formalize a natural (distribution-free) solution concept: given anticipated miscalibration of $\alpha$, we propose using the threshold $j$ that minimizes the worst-case regret over all $\alpha$-miscalibrated predictors, where the regret is the difference in clinical utility between using the threshold in question and using the optimal threshold in hindsight.
On Computationally Efficient Multi-Class Calibration
Projected smooth calibration gives strong guarantees for all downstream decision makers who want to use the predictor for binary classification problems of the form: does the label belong to a subset $T \subseteq [k]$: e. g. is this an image of an animal?
