Ensuring safety in optimization is challenging if the underlying functional forms of either the constraints or the objective function are unknown. The challenge can be addressed by using Gaussian processes to provide confidence intervals used to find solutions that can be considered safe. To iteratively find a trade-off between finding the solution and ensuring safety, the SafeOpt algorithm builds on algorithms using only the upper bounds (UCB-type algorithms) by performing an exhaustive search on the entire search space to find a safe iterate. That approach can quickly become computationally expensive. We reformulate the exhaustive search as a series of optimization problems to find the next recommended points. We show that the proposed reformulation allows using a wide range of available optimization solvers, such as derivative-free methods. We show that by exploiting the properties of the solver, we enable the introduction of new stopping criteria into safe learning methods and increase flexibility in trading off solver accuracy and computational time. The results from a non-convex optimization problem and an application for controller tuning confirm the flexibility and the performance of the proposed reformulation.

We consider network aggregative games where each player minimizes a cost function that depends on its own strategy and on a convex combination of the strategies of its neighbors. As a first contribution, we propose a class of distributed algorithms that can be used to steer the strategies of the rational agents to a Nash equilibrium configuration, with guaranteed convergence under different sufficient conditions depending on the cost functions and on the network. A distinctive feature of the proposed class of algorithms is that agents use optimal responses instead of gradient type of strategy updates. As a second contribution, we show that the algorithm suggested for network aggregative games can also be used to recover a Nash equilibrium of average aggregative games (i.e., games where each agent is affected by the average of the strategies of the whole population) in a distributed fashion, that is, without requiring a central coordinator. We apply our theoretical results to multi-dimensional, convex-constrained opinion dynamics and to demand-response schemes for energy management.

We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel approximation scheme using a smoothed fast gradient method that is equipped with explicit bounds on the approximation error. We further demonstrate how the presented scheme can be used for approximating the chemical master equation through the zero-information moment closure method, and for an approximate dynamic programming approach in the context of constrained Markov decision processes with uncountable state and action spaces.

We present an approximation method to a class of parametric integration problems that naturally appear when solving the dual of the maximum entropy estimation problem. Our method builds up on a recent generalization of Gauss quadratures via an infinite-dimensional linear program, and utilizes a convex clustering algorithm to compute an approximate solution which requires reduced computational effort. It shows to be particularly appealing when looking at problems with unusual domains and in a multi-dimensional setting. As a proof of concept we apply our method to an example problem on the unit disc.

This article presents an approximation scheme for the infinite-dimensional linear programming formulation of discrete-time Markov control processes via a finite-dimensional convex program, when the dynamics are unknown and learned from data. We derive a probabilistic explicit error bound between the data-driven finite convex program and the original infinite linear program. We further discuss the sample complexity of the error bound which translates to the number of samples required for an a priori approximation accuracy. Our analysis sheds light on the impact of the choice of basis functions for approximating the true value function. Finally, the relevance of the method is illustrated on a truncated LQG problem.

This article presents a novel perspective along with a scalable methodology to design a fault detection and isolation (FDI) filter for high dimensional nonlinear systems. Previous approaches on FDI problems are either confined to linear systems or they are only applicable to low dimensional dynamics with specific structures. In contrast, shifting attention from the system dynamics to the disturbance inputs, we propose a relaxed design perspective to train a linear residual generator given some statistical information about the disturbance patterns. That is, we propose an optimization-based approach to robustify the filter with respect to finitely many signatures of the nonlinearity. We then invoke recent results in randomized optimization to provide theoretical guarantees for the performance of the proposed filer. Finally, motivated by a cyber-physical attack emanating from the vulnerabilities introduced by the interaction between IT infrastructure and power system, we deploy the developed theoretical results to detect such an intrusion before the functionality of the power system is disrupted.

We consider the Scenario Convex Program (SCP) for two classes of optimization problems that are not tractable in general: Robust Convex Programs (RCPs) and Chance-Constrained Programs (CCPs). We establish a probabilistic bridge from the optimal value of SCP to the optimal values of RCP and CCP in which the uncertainty takes values in a general, possibly infinite dimensional, metric space. We then extend our results to a certain class of non-convex problems that includes, for example, binary decision variables. In the process, we also settle a measurability issue for a general class of scenario programs, which to date has been addressed by an assumption. Finally, we demonstrate the applicability of our results on a benchmark problem and a problem in fault detection and isolation.