no code implementations • 6 Apr 2024 • Hamidreza Montaseri, Amin Gohari
The proliferation of algorithmic systems has fueled discussions surrounding the regulation and control of their social impact.
no code implementations • 28 Feb 2024 • Haoyu Lei, Amin Gohari, Farzan Farnia
Finally, we present several numerical results on the application of DP-based learning methods to standard centralized and distributed learning problems.
no code implementations • 21 Jun 2022 • Saeed Masiha, Amin Gohari, Mohammad Hossein Yassaee
In this paper, we provide three applications for $f$-divergences: (i) we introduce Sanov's upper bound on the tail probability of the sum of independent random variables based on super-modular $f$-divergence and show that our generalized Sanov's bound strictly improves over ordinary one, (ii) we consider the lossy compression problem which studies the set of achievable rates for a given distortion and code length.
no code implementations • 4 Mar 2022 • Milad Sefidgaran, Amin Gohari, Gaël Richard, Umut Şimşekli
Understanding generalization in modern machine learning settings has been one of the major challenges in statistical learning theory.
no code implementations • 10 Feb 2021 • Mohammad Saeed Masiha, Amin Gohari, Mohammad Hossein Yassaee, Mohammad Reza Aref
We study learning algorithms when there is a mismatch between the distributions of the training and test datasets of a learning algorithm.
Information Theory Information Theory