555 citations · 2.5k across the 105 of their papers we have counts for
7 papers · 1 filter
Minimal Reachability is Hard To Approximate
Ali Jadbabaie, Alexander Olshevsky, George J. Pappas +1
In this note, we consider the problem of choosing which nodes of a linear dynamical system should be actuated so that the state transfer from the system's initial condition to a gi…
Sensing-Constrained LQG Control
Vasileios Tzoumas, Luca Carlone, George J. Pappas +1
Linear-Quadratic-Gaussian (LQG) control is concerned with the design of an optimal controller and estimator for linear Gaussian systems with imperfect state information. Standard L…
Network Inference from Consensus Dynamics
Santiago Segarra, Michael T. Schaub, Ali Jadbabaie
We consider the problem of identifying the topology of a weighted, undirected network from observing snapshots of multiple independent consensus dynamics. Specifically…
Global optimality conditions for deep neural networks
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, a…
Bayesian Decision Making in Groups is Hard
Jan Hązła, Ali Jadbabaie, Elchanan Mossel +1
We study the computations that Bayesian agents undertake when exchanging opinions over a network. The agents act repeatedly on their private information and take myopic actions tha…
Resilient Monotone Submodular Function Maximization
Vasileios Tzoumas, Konstantinos Gatsis, Ali Jadbabaie +1
In this paper, we focus on applications in machine learning, optimization, and control that call for the resilient selection of a few elements, e.g. features, sensors, or leaders,…