265 citations · 1k across the 84 of their papers we have counts for
7 papers · 1 filter
Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes
Sina Baharlouei, Fatemeh Sheikholeslami, Meisam Razaviyayn +1
This work concerns the development of deep networks that are certifiably robust to adversarial attacks. Joint robust classification-detection was recently introduced as a certified…
Stochastic Differentially Private and Fair Learning
Andrew Lowy, Devansh Gupta, Meisam Razaviyayn
Machine learning models are increasingly used in high-stakes decision-making systems. In such applications, a major concern is that these models sometimes discriminate against cert…
Tradeoffs between convergence rate and noise amplification for momentum-based accelerated optimization algorithms
Hesameddin Mohammadi, Meisam Razaviyayn, Mihailo R. Jovanović
We study momentum-based first-order optimization algorithms in which the iterations utilize information from the two previous steps and are subject to an additive white noise. This…
Private Stochastic Optimization With Large Worst-Case Lipschitz Parameter
Andrew Lowy, Meisam Razaviyayn
We study differentially private (DP) stochastic optimization (SO) with loss functions whose worst-case Lipschitz parameter over all data may be extremely large or infinite. To date…
Congestion Reduction via Personalized Incentives
Ali Ghafelebashi, Meisam Razaviyayn, Maged Dessouky
With rapid population growth and urban development, traffic congestion has become an inescapable issue, especially in large cities. Many congestion reduction strategies have been p…
Private Non-Convex Federated Learning Without a Trusted Server
Andrew Lowy, Ali Ghafelebashi, Meisam Razaviyayn
We study federated learning (FL) -- especially cross-silo FL -- with non-convex loss functions and data from people who do not trust the server or other silos. In this setting, eac…
A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions
Daniel Lundstrom, Tianjian Huang, Meisam Razaviyayn
As deep learning (DL) efficacy grows, concerns for poor model explainability grow also. Attribution methods address the issue of explainability by quantifying the importance of an…