Can I read Online Contextual Decision-Making with a Smart Predict-then-Optimize Method on EtoBox?

Online Contextual Decision-Making with a Smart Predict-then-Optimize Method by Liu, Heyuan; Grigas, Paul is a scholarly article available to read on EtoBox.

What is Online Contextual Decision-Making with a Smart Predict-then-Optimize Method about?

We study an online contextual decision-making problem with resource constraints. At each time period, the decision-maker first predicts a reward vector and resource consumption matrix based on a given context vector and then solves a downstream optimization problem to make a decision. The final goal of the decision-maker is to maximize the summation of the reward and the utility from resource consumption, while satisfying the resource constraints. We propose an algorithm that mixes a prediction step based on the "Smart Predict-then-Optimize (SPO)" method with a dual update step based on mirror descent. We prove regret bounds and demonstrate that the overall convergence rate of our method depends on the $\mathcal{O}(T^{-1/2})$ convergence of online mirror descent as well as risk bounds of the surrogate loss function used to learn the prediction model. Our algorithm and regret bounds apply to a general convex feasible region for the resource constraints, including both hard and soft resource constraint cases, and they apply to a wide class of prediction models in contrast to the traditional settings of linear contextual models or finite policy spaces. We also conduct numerical experi

Author

Liu, Heyuan; Grigas, Paul

Published

2022

Language

EN