4 January 2021 in Mathematical Programming
14 September 2020 in Optimization Methods and Software
We develop and analyse a variant of the SARAH algorithm, which does not require computation of the exact gradient. Thus this new method can be applied to general expectation minimization problems rather than only finite sum problems. While the original SARAH algorithm, as well as its predecessor, SVRG, requires an exact gradient computation on each outer iteration, the inexact variant of SARAH (iSARAH), which we develop here, requires only stochastic gradient computed on a mini-batch of sufficient size. The proposed method combines variance reduction via sample size selection and iterative stochastic gradient updates. We analyse the convergence rate of the algorithms for strongly convex and non-strongly convex cases, under smooth assumption with appropriate mini-batch size selected for each case. We show that with an additional, reasonable, assumption iSARAH achieves the best-known complexity among stochastic methods in the case of non-strongly convex stochastic functions.
20 May 2022 in Computational Optimization and Applications
27 December 2021 in IEEE Access
Adversarial machine learning defenses have primarily been focused on mitigating static, white-box attacks. However, it remains an open question whether such defenses are robust under an adaptive black-box adversary. In this paper, we specifically focus on the black-box threat model and make the following contributions: First we develop an enhanced adaptive black-box attack which is experimentally shown to be ≥ 30% more effective than the original adaptive black-box attack proposed by Papernot et al. For our second contribution, we test 10 recent defenses using our new attack and propose our own black-box defense (barrier zones). We show that our defense based on barrier zones offers significant improvements in security over state-of-the-art defenses. This improvement includes greater than 85% robust accuracy against black-box boundary attacks, transfer attacks and our new adaptive black-box attack, for the datasets we study. For completeness, we verify our claims through extensive experimentation with 10 other defenses using three adversarial models (14 different black-box attacks) on two datasets (CIFAR-10 and Fashion-MNIST).
26 March 2014 in International Business Research
The topic of CEO compensation has been highly debatable. The financial crisis of 2008 further prompted public and media to question executive compensation practices in the United States. This study investigates the effect of the financial crisis on CEO compensation and also examines various determinants of CEO compensation. Using a sample of Fortune 500 firms and 2241 observations, we find that financial crisis has a small but significant effect on CEO compensation. Firm performance, firm size, and CEO duality were found to have a significant effect on CEO compensation both pre and post-crisis. One major difference found between pre and post-crisis was in the composition of pay. While cash compensation decreased significantly post-crisis, equity-compensation increased.
22 November 2017 in Queueing Systems