Posteriori Probabilistic Bounds of Convex Scenario Programs with Validation Tests

by   Chao Shang, et al.

Scenario programs have established themselves as efficient tools towards decision-making under uncertainty. To assess the quality of scenario-based solutions a posteriori, validation tests based on Bernoulli trials have been widely adopted in practice. However, to reach a theoretically reliable conclusion, one typically needs to collect massive validation samples. In this work, we propose new posteriori bounds for convex scenario programs with validation tests, which are dependent on both realizations of support constraints and performance on out-of-sample validation data. The proposed bounds enjoy wide generality in that many existing theoretical results can be incorporated as particular cases. To facilitate practical use, a systematic approach for parameterizing posteriori probability functions is also developed, which is shown to possess a variety of desirable properties allowing for easy implementations and clear interpretations. By synthesizing information about support constraints and validation tests, less conservative estimates of reliability levels can be attained for randomized solutions in comparison with existing posteriori bounds. Case studies on controller design of aircraft lateral motion are presented to validate the effectiveness of the proposed posteriori bounds.


Explicit and efficient error estimation for convex minimization problems

We combine a systematic approach for deriving general a posteriori error...

Margin theory for the scenario-based approach to robust optimization in high dimension

This paper deals with the scenario approach to robust optimization. This...

A posteriori analysis for a mixed FEM discretization of the linear elasticity spectral problem

In this paper we analyze a posteriori error estimates for a mixed formul...

Anisotropic a posteriori error estimate for the Virtual Element Method

We derive an anisotropic a posteriori error estimate for the adaptive co...

A posteriori superlinear convergence bounds for block conjugate gradient

In this paper, we extend to the block case, the a posteriori bound showi...

A study of defect-based error estimates for the Krylov approximation of φ-functions

Prior recent work, devoted to the study of polynomial Krylov techniques ...

Please sign up or login with your details

Forgot password? Click here to reset