Incentivizing Compliance with Algorithmic Instruments
Daniel Ngo * 1 Logan Stapleton * 1 Vasilis Syrgkanis 2 Zhiwei Steven Wu 3
Abstract causal effects rely on randomized experiments, which ran-
Randomized experiments can be susceptible to domly assign each individual in a population to a treatment
selection bias due to potential non-compliance by group or a control group and then estimate the causal effects
the participants. While ...


雷达卡




京公网安备 11010802022788号







