Rui Gao

Convergence of Mean-Field Langevin Stochastic Descent-Ascent for Distributional Minimax Optimization

  • Rui Gao
    • Categories Stochastic Programming

    We study convergence properties of the discrete-time Mean-Field Langevin Stochastic Descent-Ascent (MFL-SDA) algorithm for solving distributional minimax optimization. These problems arise in various applications, such as zero-sum games, generative adversarial networks and distributionally robust learning. Despite the significance of MFL-SDA in these contexts, the discrete-time convergence rate remains underexplored. To address this gap, we establish … Read more

    Wasserstein Regularization for 0-1 Loss

  • Rui Gao
    • Categories Data Science Theory, Robust Optimization, Stochastic Programming

    Wasserstein distributionally robust optimization (DRO) finds robust solutions by hedging against data perturbation specified by distributions in a Wasserstein ball. The robustness is linked to the regularization effect, which has been studied for continuous losses in various settings. However, existing results cannot be simply applied to the 0-1 loss, which is frequently seen in uncertainty … Read more

    Decision-making with Side Information: A Causal Transport Robust Approach

  • Jincheng Yang
  • Luhao Zhang
  • Ningyuan Chen
  • Rui Gao
  • Ming Hu
    • Categories Optimization in Data Science, Robust Optimization, Stochastic Programming Tags , , ,

    We consider stochastic optimization with side information where, prior to decision making, covariate data are available to inform better decisions. In particular, we propose to consider a distributionally robust formulation based on causal transport distance. Compared with divergence and Wasserstein metric, the causal transport distance is better at capturing the information structure revealed from the conditional distribution … Read more

    Data-driven Multistage Distributionally Robust Linear Optimization with Nested Distance

  • Rui Gao
    • Categories Dynamic Programming, Robust Optimization, Stochastic Programming Tags , , ,

    We study multistage distributionally robust linear optimization, where the uncertainty set is defined as a ball of distribution centered at a scenario tree using the nested distance. The resulting minimax problem is notoriously difficult to solve due to its inherent non-convexity. In this paper, we demonstrate that, under mild conditions, the robust risk evaluation of … Read more

    Optimal Robust Policy for Feature-Based Newsvendor

  • Luhao Zhang
  • Jincheng Yang
  • Rui Gao
    • Categories Infinite Dimensional Optimization, Robust Optimization, Supply Chain Management Tags , , ,

    We study policy optimization for the feature-based newsvendor, which seeks an end-to-end policy that renders an explicit mapping from features to ordering decisions. Unlike existing works that restrict the policies to some parametric class which may suffer from sub-optimality (such as affine class) or lack of interpretability (such as neural networks), we aim to optimize … Read more

    Statistical Inference of Contextual Stochastic Optimization with Endogenous Uncertainty

  • Junyu Cao
  • Rui Gao
    • Categories Robust Optimization, Statistics, Stochastic Programming Tags

    This paper considers contextual stochastic optimization with endogenous uncertainty, where random outcomes depend on both contextual information and decisions. We analyze the statistical properties of solutions from two prominent approaches: predict-then-optimize (PTO), which first predicts a model between outcomes, contexts, and decisions, and then optimizes the downstream objective; and estimate- then-optimize (ETO), which directly estimates … Read more

    Sinkhorn Distributionally Robust Optimization

  • Jie Wang
  • Rui Gao
  • Yao Xie
    • Categories Infinite Dimensional Optimization, Robust Optimization, Stochastic Programming

    We study distributionally robust optimization with Sinkhorn distance—a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased subgradient estimators and derive its computational complexity guarantees. Finally, … Read more

    Reliable Off-policy Evaluation for Reinforcement Learning

  • Rui Gao
  • Jie Wang
  • Hongyuan Zha
    • Categories Robust Optimization

    In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy. Reinforcement learning in high-stake environments, such as healthcare and education, is often limited to off-policy settings due to safety or ethical concerns, or … Read more

    Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality

  • Rui Gao
    • Categories Robust Optimization, Statistics, Stochastic Programming Tags , , , ,

    Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable solutions by hedging against data perturbations in Wasserstein distance. Despite its recent empirical success in operations research and machine learning, existing performance guarantees for generic loss functions are either overly conservative due to the curse of dimensionality, or plausible only in large sample asymptotics. … Read more

    Wasserstein Distributionally Robust Optimization and Variation Regularization

  • Xi Chen
  • Rui Gao
  • Anton J. Kleywegt
    • Categories Applications - OR and Management Sciences, Robust Optimization, Stochastic Programming

    Wasserstein distributionally robust optimization (DRO) has recently achieved empirical success for various applications in operations research and machine learning, owing partly to its regularization effect. Although the connection between Wasserstein DRO and regularization has been established in several settings, existing results often require restrictive assumptions, such as smoothness or convexity, that are not satisfied by … Read more