3 papers
cs.LG2025
Distributional Adversarial Loss
Saba Ahmadi, Siddharth Bhandari, Avrim Blum +2
We initiate the study of a new notion of adversarial loss which we call distributional adversarial loss. In this notion, we assume for each original example, the allowed adversaria…
cs.LG2025
Verifying Classification with Limited Disclosure
Siddharth Bhandari, Liren Shan
We consider the multi-party classification problem introduced by Dong, Hartline, and Vijayaraghavan (2022) motivated by electronic discovery. In this problem, our goal is to design…
cs.LG2024
Replicable Online Learning
Saba Ahmadi, Siddharth Bhandari, Avrim Blum
We investigate the concept of algorithmic replicability introduced by Impagliazzo et al. 2022, Ghazi et al. 2021, Ahn et al. 2024 in an online setting. In our model, the input sequ…