E
Erfan Nozari
Researcher at University of Pennsylvania
Publications - 39
Citations - 770
Erfan Nozari is an academic researcher from University of Pennsylvania. The author has contributed to research in topics: Network controllability & Complex network. The author has an hindex of 10, co-authored 33 publications receiving 425 citations. Previous affiliations of Erfan Nozari include University of California, San Diego & University of California, Riverside.
Papers
More filters
Journal ArticleDOI
Differentially private average consensus
TL;DR: In this article, a differentially private Laplacian consensus algorithm was proposed for the multi-agent average consensus problem under the requirement of differential privacy of the agents initial states against an adversary that has access to all the messages.
Journal ArticleDOI
Differentially Private Distributed Convex Optimization via Functional Perturbation
TL;DR: The impossibility of achieving differential privacy is proved using strategies based on perturbing the inter-agent messages with noise when the underlying noise-free dynamics are asymptotically stable, justifying the algorithmic solution based on the perturbation of individual functions with Laplace noise.
Journal ArticleDOI
Teaching recurrent neural networks to infer global temporal structure from local examples
Jason Z. Kim,Zhixin Lu,Erfan Nozari,Erfan Nozari,George J. Pappas,Danielle S. Bassett,Danielle S. Bassett +6 more
TL;DR: It is demonstrated that a recurrent neural network (RNN) can learn to modify its representation of complex information using only examples, and the associated learning mechanism is explained with new theory.
Journal ArticleDOI
Differentially Private Average Consensus with Optimal Noise Selection
TL;DR: An impossibility result is established that shows that exact average consensus cannot be achieved by any algorithm that preserves differential privacy, which motives the design of a differentially private discrete-time distributed algorithm that corrupts messages with Laplacian noise and is guaranteed to achieve average consensus in expectation.
Posted ContentDOI
Is the brain macroscopically linear? A system identification of resting state dynamics
Erfan Nozari,Jennifer Stiso,Lorenzo Caciagli,Eli J. Cornblath,Xiaosong He,Maxwell A. Bertolero,Arun S. Mahadevan,George J. Pappas,Danielle S. Bassett +8 more
TL;DR: In this article, the authors provide a rigorous and data-driven answer at the level of whole-brain bloodoxygen-level-dependent (BOLD) and macroscopic field potential dynamics by leveraging the theory of system identification.