no code implementations • 28 Feb 2022 • Palash Dey, Debajyoti Kar, Swagato Sanyal
We complement this result by proving that any algorithm, from a natural class of algorithms, for predicting the winner in a district-based election when $r$ is plurality, must sample at least $\Omega\left(\frac{1}{\varepsilon^4}\log\frac{1}{\delta}\right)$ votes.
no code implementations • 9 Sep 2021 • Debajyoti Kar, Mert Kosan, Debmalya Mandal, Sourav Medya, Arlei Silva, Palash Dey, Swagato Sanyal
Ensuring fairness in machine learning algorithms is a challenging and essential task.