Corrado Possieri

Corrado Possieri

Auto-generated profile, based on publicly available information

Corrado Possieri

Dipartimento di Ingegneria Civile e Ingegneria Informatica, Universit degli Studi di Roma Tor Vergata, Rome, Italy

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 May 2019 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
GCGiuseppe C. Calafiore
Giuseppe C. Calafiore
SGStephane Gaubert
Stephane Gaubert
CPCorrado Possieri
Corrado Possieri
In this paper, we show that a one-layer feedforward neural network with exponential activation functions in the inner layer and logarithmic activation in the output neuron is a universal approximator of convex functions. Such a network represents a family of scaled log-sum exponential functions, here named log-sum-exp (LSET). Under a suitable exponential transformation, the class of LSET functions maps to a family of generalized posynomials GPOST, which we similarly show to be universal approximators for log-log-convex functions. A key feature of an LSET network is that, once it is trained on data, the resulting model is convex in the variables, which makes it readily amenable to efficient design based on convex optimization. Similarly, once a GPOST model is trained on data, it yields a posynomial model that can be efficiently optimized with respect to its variables by using geometric programming (GP). The proposed methodology is illustrated by two numerical examples, in which, first, models are constructed from simulation data of the two physical processes (namely, the level of vibration in a vehicle suspension system, and the peak power generated by the combustion of propane), and then optimization-based design is performed on these models.

11 March 2020 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
GCGiuseppe C. Calafiore
Giuseppe C. Calafiore
SGStephane Gaubert
Stephane Gaubert
CPCorrado Possieri
Corrado Possieri
We show that a neural network whose output is obtained as the difference of the outputs of two feedforward networks with exponential activation function in the hidden layer and logarithmic activation function in the output node, referred to as log-sum-exp (LSE) network, is a smooth universal approximator of continuous functions over convex, compact sets. By using a logarithmic transform, this class of network maps to a family of subtraction-free ratios of generalized posynomials (GPOS), which we also show to be universal approximators of positive functions over log-convex, compact subsets of the positive orthant. The main advantage of difference-LSE networks with respect to classical feedforward neural networks is that, after a standard training phase, they provide surrogate models for a design that possesses a specific difference-of-convex-functions form, which makes them optimizable via relatively efficient numerical methods. In particular, by adapting an existing difference-of-convex algorithm to these models, we obtain an algorithm for performing an effective optimization-based design. We illustrate the proposed approach by applying it to the data-driven design of a diet for a patient with type-2 diabetes and to a nonconvex optimization problem.

12 October 2016 in IEEE Transactions on Automatic Control
Verified
Journal Article
Open access
CPCorrado Possieri
Corrado Possieri
ATAndrew R. Teel
Andrew R. Teel
In this paper, we deal with the problem of output feedback stabilization for a class of linear hybrid systems. This problem is addressed by characterizing the structural properties of such a class of systems. Namely, reachability, controllability, stabilizability, observability, constructibility, and detectability are framed in terms of algebraic and geometric conditions on the data of the system. Two canonical forms, recalling the classical Kalman decompositions with respect to reachability and observability, are given. By taking advantage of this characterization, duality between control and observation structural properties is established and necessary and sufficient conditions for the existence of a linear time-invariant output feedback compensator are stated. Compared with previous results, no assumption is needed on the plant about minimum phaseness, relative degree, or squareness.

7 February 2022 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
CPCorrado Possieri
Corrado Possieri
MSMario Sassano
Mario Sassano
A data-driven strategy to estimate the optimal feedback and the value function in an infinite-horizon, continuous-time, linear-quadratic optimal control problem for an unknown system is proposed. The method permits the construction of the optimal policy without any knowledge of the model, without requiring that the time derivatives of the state are available for the design, and without even assuming that an initial stabilizing feedback policy is available. Two alternative architectures are discussed: the first scheme revolves around the periodic computation of some matrix inversions involving the Q-function, whereas the second approach relies on a purely continuous-time implementation of some dynamic systems whose trajectories are uniformly attracted by the solutions to the above algebraic equations. Interestingly, the proposed strategy essentially constitutes a (direct) data-driven implementation of the celebrated Kleinman algorithm, hence subsuming the particularly appealing features of the latter, such as quadratic monotone convergence to the optimal solution. The theory is then validated by the means of practically motivated applications.

3 August 2020 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
GCGiuseppe C. Calafiore
Giuseppe C. Calafiore
CPCorrado Possieri
Corrado Possieri
An algorithm is proposed to determine output feedback policies that solve finite-horizon linear-quadratic (LQ) optimal control problems without requiring knowledge of the system dynamical matrices. To reach this goal, the Q-factors arising from finite-horizon LQ problems are first characterized in the state feedback case. It is then shown how they can be parameterized as functions of the input-output vectors. A procedure is then proposed for estimating these functions from input/output data and using these estimates for computing the optimal control via the measured inputs and outputs.

9 June 2017 in Asian Journal of Control
Verified
Journal Article
Closed access
PDF file
LMLaura Menini
Laura Menini
CPCorrado Possieri
Corrado Possieri
ATAntonio Tornambè
Antonio Tornambè