This paper considers data-driven chance-constrained stochastic optimization problems in a Bayesian framework. posteriors afford principled mechanism to incorporate data and prior knowledge into problems. However, the computation of is typically an intractable problem, has spawned large literature on approximate computation. Here, context optimization, we focus question statistical consistency (...

In this paper we consider finite-horizon predictive control of dynamic systems subject to stochastic uncertainty; such uncertainty arises due to exogenous disturbances, modeling errors, and sensor noise. Stochastic robustness is typically defined using chance constraints, which require that the probability of state constraints being violated is below a prescribed value. Prior work showed that i...

This paper studies the problem of constructing robust classifiers when the training is plagued with uncertainty. The problem is posed as a Chance-Constrained Program (CCP) which ensures that the uncertain datapoints are classified correctly with high probability. Unfortunately such a CCP turns out to be intractable. The key novelty is in employing Bernstein bounding schemes to relax the CCP as ...

We consider fuzzy stochastic programming problems with a crisp objective function and linear constraints whose coefficients are fuzzy random variables, in particular of type L-R. To solve this type of problems, we formulate deterministic counterparts of chance-constrained programming with fuzzy stochastic coefficients, by combining constraints on probability of satisfying constraints, as well a...

Autonomous agents operating in partially observable stochastic environments often face the problem of optimizing expected performance while bounding the risk of violating safety constraints. Such problems can be modeled as chance-constrained POMDP’s (CCPOMDP’s). Our first contribution is a systematic derivation of execution risk in POMDP domains, which improves upon how chance constraints are h...