no code implementations • 19 Feb 2024 • Usama Muneeb, Mesrob I. Ohannessian
We consider scenarios where a very accurate predictive model using restricted features is available at the time of training of a larger, full-featured, model.
1 code implementation • ICML 2020 • Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro
Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations.
no code implementations • 7 Dec 2018 • Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro
In this paper, we propose a simple yet revealing model that encompasses (1) a selection process where an institution chooses from multiple groups according to their qualifications so as to maximize an institutional utility and (2) dynamics that govern the evolution of the groups' qualifications according to the imposed policies.
no code implementations • NeurIPS 2017 • Moein Falahatgar, Mesrob I. Ohannessian, Alon Orlitsky, Venkatadheeraj Pichapati
Minimax optimality is too pessimistic to remedy this issue.
no code implementations • 20 Feb 2017 • Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, Nathan Srebro
We consider learning a predictor which is non-discriminatory with respect to a "protected attribute" according to the notion of "equalized odds" proposed by Hardt et al. [2016].
no code implementations • NeurIPS 2016 • Moein Falahatgar, Mesrob I. Ohannessian, Alon Orlitsky
Utilizing the structure of a probabilistic model can significantly increase its learning speed.
no code implementations • 2 May 2016 • Mario Lucic, Mesrob I. Ohannessian, Amin Karbasi, Andreas Krause
Using k-means clustering as a prototypical unsupervised learning problem, we show how we can strategically summarize the data (control space) in order to trade off risk and time when data is generated by a probabilistic model.
no code implementations • 12 Mar 2015 • Elchanan Mossel, Mesrob I. Ohannessian
The probability of this event is referred to as the "missing mass".