Now showing items 1-2 of 2

    • Constant Depth Decision Rules for Multistage Stochastic Convex Programs 

      Guigues, Vincent Gérard Yannick; Juditsky, Anatoli; Nemirovski, Arkadi Semenovich
      2020-05
      In this paper, we introduce a new class of decision rules called Constant Depth Decision Rules (CDDRs) for Multistage Stochastic Convex Programs (MSCP) depending on a parame- ter Mi called the depth of the decision rules. ...
    • Non-asymptotic confidence bounds for the optimal value of a stochastic program 

      Guigues, Vincent Gérard Yannick; Juditsky, Anatoli; Nemirovski, Arkadi Semenovich
      2016
      We discuss a general approach to building non-asymptotic confidence bounds for stochastic optimization problems. Our principal contribution is the observation that a Sample Average Approximation of a problem supplies upper ...