no code implementations • 14 Oct 2023 • Nicolo Cesa-Bianchi, Roberto Colomboni, Maximilian Kasy
This implies that (i) welfare maximization is harder than the multi-armed bandit problem (with a rate of $T^{1/2}$ for finite policy sets), and (ii) our algorithm achieves the optimal rate.
no code implementations • 20 Aug 2022 • Maximilian Kasy, Jann Spiess
We show that implementation requires pre-analysis plans.
no code implementations • 4 Nov 2020 • Maximilian Kasy, Alexander Teytelboym
We consider settings where an allocation has to be chosen repeatedly, returns are unknown but can be learned, and decisions are subject to constraints.
1 code implementation • 2 Mar 2020 • Ashia Wilson, Maximilian Kasy, Lester Mackey
Cross-validation (CV) is a popular approach for assessing and selecting predictive models.
no code implementations • 31 Mar 2017 • Alberto Abadie, Maximilian Kasy
To address (ii), we show that data-driven choices of regularization parameters, based on Stein's unbiased risk estimate or on cross-validation, yield estimators with risk uniformly close to the risk attained under the optimal (unfeasible) choice of regularization parameters.