5 accepted papers
We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, $\Pi$net, leverages operator splitting for rapid and reliable projections in the forward pass, and the implicit function theorem for backpropagation. We deploy $\Pi$net as a feasible-by-de…
We address the challenge of sequential data-driven decision-making under context distributional uncertainty. This problem arises in numerous real-world scenarios where the learner optimizes black-box objective functions in the presence of uncontrollable contextual variables. We consider the setting…
In this paper, we study the problem of online tracking in linear control systems, where the objective is to follow a moving target. Unlike classical tracking control, the target is unknown, non-stationary, and its state is revealed sequentially, thus, fitting the framework of online non-stochastic c…
Controller tuning and parameter optimization are crucial in system design to improve both the controller and underlying system performance. Bayesian optimization (BO) has been established as an efficient model-free method for controller tuning and adaptation. Standard methods, however, are not enoug
An important issue in anomaly detection in smart manufacturing systems is the lack of consistency in the formal definitions of anomalies, faults, and attacks. The term anomaly is used to cover a wide range of situations that are addressed by different types of solutions. In this letter, we categoriz