1 code implementation • 20 Oct 2022 • Mikhail Khodak, Kareem Amin, Travis Dick, Sergei Vassilvitskii
When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors.
no code implementations • 15 Aug 2022 • Kareem Amin, Matthew Joseph, Mónica Ribero, Sergei Vassilvitskii
In this paper, we study an algorithm which uses the exponential mechanism to select a model with high Tukey depth from a collection of non-private regression models.
no code implementations • NeurIPS 2021 • Kareem Amin, Giulia Desalvo, Afshin Rostamizadeh
Consider a setting where we wish to automate an expensive task with a machine learning algorithm using a limited labeling resource.
no code implementations • NeurIPS 2021 • Daniel Levy, Ziteng Sun, Kareem Amin, Satyen Kale, Alex Kulesza, Mehryar Mohri, Ananda Theertha Suresh
We show that for high-dimensional mean estimation, empirical risk minimization with smooth losses, stochastic convex optimization, and learning hypothesis classes with finite metric entropy, the privacy cost decreases as $O(1/\sqrt{m})$ as users provide more samples.
no code implementations • NeurIPS 2019 • Kareem Amin, Travis Dick, Alex Kulesza, Andres Munoz, Sergei Vassilvitskii
The covariance matrix of a dataset is a fundamental statistic that can be used for calculating optimum regression weights as well as in many other learning and data analysis settings.
no code implementations • 4 Nov 2019 • Kareem Amin, Matthew Joseph, Jieming Mao
We show that the sample complexity of pure pan-private uniformity testing is $\Theta(k^{2/3})$.
no code implementations • NeurIPS 2017 • Kareem Amin, Nan Jiang, Satinder Singh
We introduce a novel repeated Inverse Reinforcement Learning problem: the agent has to act on behalf of a human in a sequence of tasks and wishes to minimize the number of tasks that it surprises the human by acting suboptimally with respect to how the human would have acted.
no code implementations • NeurIPS 2016 • Jacob D. Abernethy, Kareem Amin, Ruihao Zhu
The learner selects one of $K$ actions (arms), this action generates a random sample from a fixed distribution, and the action then receives a unit payoff in the event that this sample exceeds the threshold value.
no code implementations • 25 Jan 2016 • Kareem Amin, Satinder Singh
We first demonstrate that if the learner can experiment with any transition dynamics on some fixed set of states and actions, then there exists an algorithm that reconstructs the agent's reward function to the fullest extent theoretically possible, and that requires only a small (logarithmic) number of experiments.
no code implementations • NeurIPS 2014 • Kareem Amin, Afshin Rostamizadeh, Umar Syed
Motivated by real-time advertising exchanges, we analyze the problem of pricing inventory in a repeated posted-price auction.
no code implementations • 27 Jul 2014 • Kareem Amin, Rachel Cummings, Lili Dworkin, Michael Kearns, Aaron Roth
We consider the problem of learning from revealed preferences in an online setting.
no code implementations • NeurIPS 2013 • Kareem Amin, Afshin Rostamizadeh, Umar Syed
Inspired by real-time ad exchanges for online display advertising, we consider the problem of inferring a buyer's value distribution for a good when the buyer is repeatedly interacting with a seller through a posted-price mechanism.