OCLGMar 25, 2022

Randomized Policy Optimization for Optimal Stopping

arXiv:2203.13446v12 citationsh-index: 15
Originality Highly original
AI Analysis

This addresses optimal stopping problems in domains like finance and healthcare, offering a novel method that improves performance over existing deterministic approaches.

The paper tackles the problem of high-dimensional optimal stopping by proposing randomized linear policies, showing that optimizing over them is equivalent to deterministic linear policies under mild conditions, and demonstrates through numerical experiments on option pricing benchmarks that the approach substantially outperforms state-of-the-art methods.

Optimal stopping is the problem of determining when to stop a stochastic system in order to maximize reward, which is of practical importance in domains such as finance, operations management and healthcare. Existing methods for high-dimensional optimal stopping that are popular in practice produce deterministic linear policies -- policies that deterministically stop based on the sign of a weighted sum of basis functions -- but are not guaranteed to find the optimal policy within this policy class given a fixed basis function architecture. In this paper, we propose a new methodology for optimal stopping based on randomized linear policies, which choose to stop with a probability that is determined by a weighted sum of basis functions. We motivate these policies by establishing that under mild conditions, given a fixed basis function architecture, optimizing over randomized linear policies is equivalent to optimizing over deterministic linear policies. We formulate the problem of learning randomized linear policies from data as a smooth non-convex sample average approximation (SAA) problem. We theoretically prove the almost sure convergence of our randomized policy SAA problem and establish bounds on the out-of-sample performance of randomized policies obtained from our SAA problem based on Rademacher complexity. We also show that the SAA problem is in general NP-Hard, and consequently develop a practical heuristic for solving our randomized policy problem. Through numerical experiments on a benchmark family of option pricing problem instances, we show that our approach can substantially outperform state-of-the-art methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes