Algorithms for stochastic optimization with functional or expectation constraints

Abstract

This paper considers the problem of minimizing an expectation function over a closed convex set, coupled with a {\color{black} functional or expectation} constraint on either decision variables or problem parameters. We first present a new stochastic approximation (SA) type algorithm, namely the cooperative SA (CSA), to handle problems with the constraint on devision variables. We show that this algorithm exhibits the optimal $\mathcal{O}(1/{\epsilon }^2)$ rate of convergence, in terms of both optimality gap and constraint violation, when the objective and constraint functions are generally convex, where $\epsilon$ denotes the optimality gap and infeasibility. Moreover, we show that this rate of convergence can be improved to $\mathcal{O}(1/\epsilon )$ if the objective and constraint functions are strongly convex. We then present a variant of CSA, namely the cooperative stochastic parameter approximation (CSPA) algorithm, to deal with the situation when the constraint is defined over problem parameters and show that it exhibits similar optimal rate of convergence to CSA. It is worth noting that CSA and CSPA are primal methods which do not require the iterations on the dual space and/or the estimation on the size of the dual variables. To the best of our knowledge, this is the first time that such optimal SA methods for solving functional or expectation constrained stochastic optimization are presented in the literature.

References in corpus (1)

• Supervised Dictionary Learning

Cited by in corpus (13)

• Online Convex Optimization with Stochastic Constraints
• Recent theoretical advances in decentralized distributed convex optimization
• Certifiable Risk-Based Engineering Design Optimization
• Primal-dual stochastic gradient method for convex programs with many functional constraints
• Conservative Stochastic Optimization with Expectation Constraints
• Inexact Proximal-Point Penalty Methods for Constrained Non-Convex Optimization
• The Online Saddle Point Problem and Online Convex Optimization with Knapsacks
• Optimal Convergence for Stochastic Optimization with Multiple Expectation Constraints
• An iterative regularized mirror descent method for ill-posed nondifferentiable stochastic optimization
• Personalized Treatment Selection using Causal Heterogeneity
• Optimization-based Calibration of Simulation Input Models
• A New Primal-Dual Algorithm for a Class of Nonlinear Compositional Convex Optimization Problems
• Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization