4 papers
Tight Sample Bounds for Renyi and Min-Entropy Estimation
Arman Adibi, Piotr Krysta
Estimating entropy from samples is fundamental in information theory and property testing. Shannon entropy measures average uncertainty and can be estimated to constant additive ac…
Convergence of Byzantine-Resilient Gradient Tracking via Probabilistic Edge Dropout
Amirhossein Dezhboro, Fateme Maleki, Arman Adibi +2
We study distributed optimization over networks with Byzantine agents that may send arbitrary adversarial messages. We propose \emph{Gradient Tracking with Probabilistic Edge Dropo…
Cascading Robustness Verification: Toward Efficient Model-Agnostic Certification
Mohammadreza Maleki, Rushendra Sidibomma, Arman Adibi +1
Certifying neural network robustness against adversarial examples is challenging, as formal guarantees often require solving non-convex problems. Hence, incomplete verifiers are wi…
Asymptotically Optimal Change Detection for Unnormalized Pre- and Post-Change Distributions
Arman Adibi, Sanjeev Kulkarni, H. Vincent Poor +2
This paper addresses the problem of detecting changes when only unnormalized pre- and post-change distributions are accessible. This situation happens in many scenarios in physics…