We study a class of cooperative multi-agent optimization problems, where each agent is associated with local action vector and cost, the goal to cooperatively find joint profile that minimizes average costs. consider setting gradient information not readily available, agents only observe their costs incurred by actions as feedback determine new actions. propose zeroth-order scheme provide expli...

In many real-world problems, first-order (FO) derivative evaluations are too expensive or even inaccessible. For solving these zeroth-order (ZO) methods that only need function often more efficient than FO sometimes the options. this paper, we propose a novel inexact augmented Lagrangian method (ZO-iALM) to solve black-box optimization which involve composite (i.e., smooth+nonsmooth) objective ...

We present Free-MESSAGEp, the first zeroth-order algorithm for convex mean-semideviation-based risk-aware learning, which is also three-level compositional stochastic optimization algorithm, whatsoever. Using a non-trivial extension of Nesterov's classical results on Gaussian smoothing, we develop Free-MESSAGEp from principles, and show that it essentially solves smoothed surrogate to original ...

The size consistency of multi-reference Møller-Plesset perturbation theory as a function of the structure of the zeroth-order Hamiltonian is studied. In calculations it is shown that the choice of projection operators to define the zeroth-order Hamiltonian is crucial. In essence whenever such a projection operator can be written as the sum of projection operators onto particular subspaces, cros...