regret

A Sound Local Regret Methodology for Online Nonconvex Composite Optimization

  • Nadav Hallak
    • Categories Applications - OR and Management Sciences, Constrained Nonlinear Optimization, Nonlinear Optimization Tags , , ,

    Online nonconvex optimization addresses dynamic and complex decision-making problems arising in real-world decision-making tasks where the optimizer’s objective evolves with the intricate and changing nature of the underlying system. This paper studies an online nonconvex composite optimization model with limited first-order access, encompassing a wide range of practical scenarios. We define local regret using a … Read more

    Regret Analysis of Block Coordinate Gradient Methods for Online Convex Programming

  • Hua Xiaoqin
  • Nobuo Yamashita
    • Categories Applications - OR and Management Sciences, Nonlinear Optimization, Stochastic Programming Tags , , ,

    In this paper, we propose two block coordinate gradient (BCG) methods for the online convex programming: the BCG method with the cyclic rule and the BCG method with the random rule. The proposed methods solve a low dimensional problem at each iteration, and hence they are efficient for large scale problems. For the proposed methods, … Read more