Lanran Fang – Optimization Online

Steering the Feedback Loop: Policy Gradients for Online Performative Optimization

Published: 2026/10/29

Global Optimization Theory, Stochastic Approaches, Stochastic Programming

Performative decision-making arises in many real-world problems where decisions influence the populations that generate future data. A major line of existing research focuses on learning performatively stable solutions. We study average-reward performative optimization, where the learner observes an evolving population through sample batches of fixed size and learns from a single continuing trajectory with unknown … Read more

Differentiating Through Moving Recourse: Feasible Policy Optimization and Finite-Sample Certification for Multistage Stochastic Programs

Published: 2026/09/27

Dynamic Programming, Energy, Stochastic Programming differentiable projection, information relaxation, moving recourse, multistage stochastic programming, optimality gap certification, pathwise gradient, policy optimization, reservoir management

Multistage stochastic programs model decisions under uncertainty where earlier decisions change later feasible sets. We propose a feasible pathwise gradient method (FeasPG) that can update the policy as new sample paths arrive. The policy proposes a decision and projects it onto the current feasible set, so every decision is feasible. We derive the full trajectory … Read more

Distributionally Robust Optimization via Targeted Integral Probability Metrics for General Data Processes

Published: 2026/05/28, Updated: 2026/07/05

Optimization in Data Science, Robust Optimization, Stochastic Programming distributionally robust optimization, heavy-tailed distributions, incomplete data, integral probability metrics, markovian data, outlier-corrupted data, semi-infinite programming

Distributionally robust optimization (DRO) provides a principled framework for decision-making under distributional uncertainty. Classical data-driven DRO frameworks typically construct ambiguity sets from distributional information, such as moment constraints, divergence neighborhoods, or Wasserstein balls, specified before the downstream loss is considered. We propose a task-aware DRO framework based on targeted integral probability metrics. The ambiguity set … Read more