47 citations · 86 across the 10 of their papers we have counts for
11 papers · 1 filter
Instance Specific Approximations for Submodular Maximization
Eric Balkanski, Sharon Qian, Yaron Singer
For many optimization problems in machine learning, finding an optimal solution is computationally intractable and we seek algorithms that perform well in practice. Since computati…
Adversarial Attacks on Binary Image Recognition Systems
Eric Balkanski, Harrison Chase, Kojin Oshiba +3
We initiate the study of adversarial attacks on models for binary (i.e. black and white) image classification. Although there has been a great deal of work on attacking models for…
An Optimal Elimination Algorithm for Learning a Best Arm
Avinatan Hassidim, Ron Kupfer, Yaron Singer
We consider the classic problem of -PAC learning a best arm where the goal is to identify with confidence an arm whose mean is an -approximation to that of the high…
Robustness from Simple Classifiers
Sharon Qian, Dimitris Kalimeris, Gal Kaplun +1
Despite the vast success of Deep Neural Networks in numerous application domains, it has been shown that such models are not robust i.e., they are vulnerable to small adversarial p…
The FAST Algorithm for Submodular Maximization
Adam Breuer, Eric Balkanski, Yaron Singer
In this paper we describe a new algorithm called Fast Adaptive Sequencing Technique (FAST) for maximizing a monotone submodular function under a cardinality constraint whose ap…
Robust Attacks against Multiple Classifiers
Juan C. Perdomo, Yaron Singer
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be f…