On Reconstructability of Quadratic Utility Functions from the Iterations in Gradient Methods
Automatica, Volume abs/1509.05500, Issue 66, 2016, Pages 254-261.
Statistical inferenceData privacyGradient methodsData confidentialityParameter identificationMore(1+)
In this paper, we consider a scenario where an eavesdropper can read the content of messages transmitted over a network. The nodes in the network are running a gradient algorithm to optimize a quadratic utility function where such a utility optimization is a part of a decision making process by an administrator . We are interested in u...More
PPT (Upload PPT)