Search Results for author:
Found 4 papers, 0 papers with code
Omnipredictors for Regression and the Approximate Rank of Convex Functions
An \textit{omnipredictor} for a class $\mathcal L$ of loss functions and a class $\mathcal C$ of hypotheses is a predictor whose predictions incur less expected loss than the best hypothesis in $\mathcal C$ for every loss in $\mathcal L$.
Faster Recalibration of an Online Predictor via Approachability
Predictive models in ML need to be trustworthy and reliable, which often at the very least means outputting calibrated probabilities.
On the Vulnerability of Fairness Constrained Learning to Malicious Noise
For example, for Demographic Parity we show we can incur only a $\Theta(\alpha)$ loss in accuracy, where $\alpha$ is the malicious noise rate, matching the best possible even without fairness constraints.
Non-Stochastic CDF Estimation Using Threshold Queries
Along the way to designing our algorithm, we consider a more general model in which the algorithm is allowed to make a limited number of simultaneous threshold queries on each sample.
