no code implementations • 2 Jun 2023 • Alexey Kurakin, Natalia Ponomareva, Umar Syed, Liam MacDermed, Andreas Terzis
An alternative approach, which this paper studies, is to use a sensitive dataset to generate synthetic data that is differentially private with respect to the original data, and then non-privately training a model on the synthetic data.
no code implementations • 12 May 2023 • Gecia Bravo-Hermsdorff, Róbert Busa-Fekete, Mohammad Ghavamzadeh, Andres Muñoz Medina, Umar Syed
For a joint distribution over many variables whose conditional independence is given by a tree, we describe algorithms for estimating Shannon entropy that require a number of samples that is linear in the number of variables, compared to the quadratic sample complexity of prior work.
no code implementations • NeurIPS Workshop LatinX_in_AI 2021 • Andres Munoz Medina, Robert Istvan Busa-Fekete, Umar Syed, Sergei Vassilvitskii
We complement the negative results with a non-parametric estimator for the true privacy loss, and apply our techniques on large-scale benchmark data to demonstrate how to achieve a desired privacy protection.
no code implementations • 5 Oct 2021 • Hossein Esfandiari, Vahab Mirrokni, Umar Syed, Sergei Vassilvitskii
We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set.
no code implementations • 2 Jul 2020 • Andrés Muñoz Medina, Umar Syed, Sergei Vassilvitskii, Ellen Vitercik
We also prove a lower bound demonstrating that the difference between the objective value of our algorithm's solution and the optimal solution is tight up to logarithmic factors among all differentially private algorithms.
no code implementations • NeurIPS 2017 • Eric Balkanski, Umar Syed, Sergei Vassilvitskii
We first show that when cost functions come from the family of submodular functions with bounded curvature, $\kappa$, the Shapley value can be approximated from samples up to a $\sqrt{1 - \kappa}$ factor, and that the bound is tight.
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 • NeurIPS 2014 • Vitaly Kuznetsov, Mehryar Mohri, Umar Syed
We give new data-dependent learning bounds for convex ensembles in the multi-class classification setting expressed in terms of the Rademacher complexities of the sub-families composing the base classifier set, and the mixture weight assigned to each sub-family.
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.
no code implementations • NeurIPS 2010 • Umar Syed, Ben Taskar
We address the problem of semi-supervised learning in an adversarial setting.
no code implementations • NeurIPS 2010 • Umar Syed, Robert E. Schapire
We provide new theoretical results for apprenticeship learning, a variant of reinforcement learning in which the true reward function is unknown, and the goal is to perform well relative to an observed expert.
no code implementations • NeurIPS 2009 • Umar Syed, Aleksandrs Slivkins, Nina Mishra
Search engines today present results that are often oblivious to recent shifts in intent.