Yongchao Liu

Asynchronous Adaptive Gradient Tracking Methods for Distributed Stochastic Optimization Problems with Decision-dependent Distributions

  • Licheng Deng
  • Yan Gao
  • Yongchao Liu
    • Categories Stochastic Programming Tags , , ,

    This paper proposes a distributed asynchronous adaptive gradient tracking method, DASYAGT, to solve the distributed stochastic optimization problems with decision-dependent distributions over directed graphs. DASYAGT employs the local adaptive gradient to estimate the gradient of the objective function and introduces the auxiliary running-sum variable to handle asynchrony. We show that the iterates generated by DASYAGT … Read more

    Gradient Tracking Methods for Distributed Stochastic Optimization Problems with Decision-dependent Distributions

  • Licheng Deng
  • Yongchao Liu
    • Categories Stochastic Programming Tags , , , ,

    This paper aims to seek the performative stable solution and the optimal solution of the distributed stochastic optimization problem with decision-dependent distributions, which is a finite-sum stochastic optimization problem over a network and the distribution depends on the decision variables. For the performative stable solution, we provide an algorithm, DSGTD-GD, which combines the distributed stochastic … Read more

    Statistical Inference for Distributed Contextual Multi-armed Bandit

  • Wuwenqing Yan
  • Yongchao Liu
    • Categories Stochastic Programming Tags , , , ,

    In this paper, we study the online statistical inference of distributed contextual multi-armed bandit problems, where the agents collaboratively learn an optimal policy by exchanging their local estimates of the global parameters with neighbors over a communication network. We propose a distributed online decision making algorithm, which balances the exploration and exploitation dilemma via the … Read more

    Confidence Region for Distributed Stochastic Optimization Problem via Stochastic Gradient Tracking Method

  • Yongchao Liu
  • Shengchao Zhao
    • Categories Stochastic Programming Tags , , , ,

    Since stochastic approximation (SA) based algorithms are easy to implement and need less memory, they are very popular in distributed stochastic optimization problems. Many works have focused on the consistency of the objective values and the iterates returned by the SA based algorithms. It is of fundamental interest to know how to quantify the uncertainty … Read more

    Discrete Approximation Scheme in Distributionally Robust Optimization

  • Yongchao Liu
  • Xiao-Ming Yuan
  • Jin Zhang
    • Categories Robust Optimization Tags , , , ,

    Discrete approximation which is the prevailing scheme in stochastic programming in the past decade has been extended to distributionally robust optimization (DRO) recently. In this paper we conduct rigorous quantitative stability analysis of discrete approximation schemes for DRO, which measures the approximation error in terms of discretization sample size. For the ambiguity set defined through … Read more

    Primal-Dual Hybrid Gradient Method for Distributionally Robust Optimization Problems

  • Yongchao Liu
  • Xiao-Ming Yuan
  • Shangzhi Zeng
  • Jin Zhang
    • Categories Robust Optimization Tags , , , ,

    We focus on the discretization approach to distributionally robust optimization (DRO) problems and propose a numerical scheme originated from the primal-dual hybrid gradient (PDHG) method that recently has been well studied in convex optimization area. Specifically, we consider the cases where the ambiguity set of the discretized DRO model is defined through the moment condition … Read more

    Distributionally Robust Reward-risk Ratio Programming with Wasserstein Metric

  • Yongchao Liu
  • Xinmin Yang
  • Jin Zhang
  • Yong Zhao
    • Categories Robust Optimization, Stochastic Programming Tags , ,

    Reward-risk ratio (RR) is a very important stock market definition. In recent years, people extend RR model as distributionally robust reward-risk ratio (DRR) to capture the situation that the investor does not have complete information on the distribution of the underlying uncertainty. In this paper, we study the DRR model where the ambiguity on the … Read more