On the computational complexity and generalization properties of multi-stage and recursive scenario programs

We discuss the computational complexity and feasibility properties of scenario based techniques for uncertain optimization programs. We consider different solution alternatives ranging from the standard scenario approach to recursive variants, and compare feasibility as a function of the total computation burden. We identify trade-offs between the different methods depending on the problem structure and the desired probability of constraint satisfaction. Our motivation for this work stems from the applicability and complexity reduction when making decisions by means of recursive algorithms. We illustrate our results on an example from the area of approximate dynamic programming

[1]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[2]  Arkadi Nemirovski,et al.  Robust optimization – methodology and applications , 2002, Math. Program..

[3]  Benjamin Van Roy,et al.  The Linear Programming Approach to Approximate Dynamic Programming , 2003, Oper. Res..

[4]  Takafumi Kanamori,et al.  Worst-Case Violation of Sampled Convex Programs for Optimization with Uncertainty , 2012, J. Optim. Theory Appl..

[5]  Lorenzo Fagiano,et al.  Randomized Solutions to Convex Programs with Multiple Chance Constraints , 2012, SIAM J. Optim..

[6]  Sergio Grammatico,et al.  On the sample size of random convex programs with structured dependence on the uncertainty , 2015, Autom..

[7]  Giuseppe Carlo Calafiore,et al.  The scenario approach to robust control design , 2006, IEEE Transactions on Automatic Control.

[8]  Panos M. Pardalos,et al.  Approximate dynamic programming: solving the curses of dimensionality , 2009, Optim. Methods Softw..

[9]  Lorenzo Fagiano,et al.  The scenario approach for Stochastic Model Predictive Control with bounds on closed-loop constraint violations , 2013, Autom..

[10]  Giuseppe Carlo Calafiore,et al.  Robust Model Predictive Control via Scenario Optimization , 2012, IEEE Transactions on Automatic Control.

[11]  John Lygeros,et al.  Multi-Agent Autonomous Surveillance: A Framework Based on Stochastic Reachability and Hierarchical Task Allocation , 2015 .

[12]  Mathukumalli Vidyasagar,et al.  A Theory of Learning and Generalization , 1997 .

[13]  John Lygeros,et al.  On the connection between compression learning and scenario based optimization , 2014, ArXiv.

[14]  Arkadi Nemirovski,et al.  Robust solutions of uncertain linear programs , 1999, Oper. Res. Lett..

[15]  Yurii Nesterov,et al.  Universal gradient methods for convex optimization problems , 2015, Math. Program..

[16]  Giuseppe Carlo Calafiore,et al.  Random Convex Programs , 2010, SIAM J. Optim..

[17]  John Lygeros,et al.  Performance Bounds for the Scenario Approach and an Extension to a Class of Non-Convex Programs , 2013, IEEE Transactions on Automatic Control.

[18]  R. Wets,et al.  Stochastic programming , 1989 .

[19]  Melvyn Sim,et al.  Tractable Approximations to Robust Conic Optimization Problems , 2006, Math. Program..

[20]  Ian R. Petersen,et al.  Robust control of uncertain systems: Classical results and recent developments , 2014, Autom..

[21]  A Gerodimos,et al.  Robust Discrete Optimization and its Applications , 1996, J. Oper. Res. Soc..

[22]  Giuseppe Carlo Calafiore,et al.  Randomized algorithms for probabilistic robustness with real and complex structured uncertainty , 2000, IEEE Trans. Autom. Control..

[23]  Dirk P. Kroese,et al.  Handbook of Monte Carlo Methods , 2011 .

[24]  John Lygeros,et al.  Approximate dynamic programming for stochastic reachability , 2013, 2013 European Control Conference (ECC).

[25]  Peter Kall,et al.  Stochastic Programming , 1995 .

[26]  Sergio Grammatico,et al.  A Scenario Approach for Non-Convex Control Design , 2014, IEEE Transactions on Automatic Control.

[27]  John Lygeros,et al.  A numerical approach to stochastic reach-avoid problems for Markov Decision Processes , 2014, ArXiv.

[28]  Giuseppe Carlo Calafiore,et al.  A survey of randomized algorithms for control synthesis and performance verification , 2007, J. Complex..

[29]  Jean-Philippe Vial,et al.  Robust Optimization , 2021, ICORES.

[30]  Giuseppe Carlo Calafiore,et al.  Random convex programs for distributed multi-agent consensus , 2013, 2013 European Control Conference (ECC).

[31]  Marco C. Campi,et al.  The Exact Feasibility of Randomized Solutions of Uncertain Convex Programs , 2008, SIAM J. Optim..

[32]  John Lygeros,et al.  Verification of discrete time stochastic hybrid systems: A stochastic reach-avoid decision problem , 2010, Autom..

[33]  Roberto Tempo,et al.  On the Sample Complexity of Probabilistic Analysis and Design Methods , 2010 .

[34]  Constantine Caramanis,et al.  Theory and Applications of Robust Optimization , 2010, SIAM Rev..

[35]  John Lygeros,et al.  Stochastic Optimization on Continuous Domains With Finite-Time Guarantees by Markov Chain Monte Carlo Methods , 2009, IEEE Transactions on Automatic Control.

[36]  Melvyn Sim,et al.  The Price of Robustness , 2004, Oper. Res..