A compression learning perspective to scenario based optimization

We investigate the connections between compression learning and scenario based optimization. We consider different constrained optimization problems affected by uncertainty represented by means of scenarios and show that the issue of providing guarantees on the probability of constraint violation reduces to a learning problem for an appropriately chosen algorithm that enjoys compression learning properties. The compression learning perspective provides a unifying framework for scenario based optimization and allows us to revisit the scenario approach and the probabilistically robust design, a recently developed technique based on a mixture of randomized and robust optimization. Our analysis shows that all optimization problems we consider here, even though they are of different type, share certain similarities, which translates on similar feasibility properties of their solutions.

[1]  Alexander Shapiro,et al.  Convex Approximations of Chance Constrained Programs , 2006, SIAM J. Optim..

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

[3]  Peng Sun,et al.  Computation of Minimum Volume Covering Ellipsoids , 2002, Oper. Res..

[4]  Sergio Grammatico,et al.  A scenario approach to non-convex control design: Preliminary probabilistic guarantees , 2014, 2014 American Control Conference.

[5]  R. Tempo,et al.  Randomized Algorithms for Analysis and Control of Uncertain Systems , 2004 .

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

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

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

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

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

[11]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[12]  Eduardo F. Camacho,et al.  Randomized Strategies for Probabilistic Solutions of Uncertain Feasibility and Optimization Problems , 2009, IEEE Transactions on Automatic Control.

[13]  J Figueira,et al.  Stochastic Programming , 1998, J. Oper. Res. Soc..

[14]  R. Tempo,et al.  On the sample complexity of randomized approaches to the analysis and design under uncertainty , 2010, Proceedings of the 2010 American Control Conference.

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

[16]  Christodoulos A. Floudas,et al.  A new robust optimization approach for scheduling under uncertainty: : I. Bounded uncertainty , 2004, Comput. Chem. Eng..

[17]  Marco C. Campi,et al.  A Sampling-and-Discarding Approach to Chance-Constrained Optimization: Feasibility and Optimality , 2011, J. Optim. Theory Appl..

[18]  John Lygeros,et al.  On the Road Between Robust Optimization and the Scenario Approach for Chance Constrained Optimization Problems , 2014, IEEE Transactions on Automatic Control.

[19]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[20]  Alexander Shapiro,et al.  Stochastic programming approach to optimization under uncertainty , 2007, Math. Program..

[21]  Sally Floyd,et al.  Sample compression, learnability, and the Vapnik-Chervonenkis dimension , 2004, Machine Learning.