arXiv subjects

Guangwu Liu

Publications and source records attributed to Guangwu Liu.

6 recordsLinked to original sources

arXiv2025

Sharpe Ratio Optimization in Markov Decision Processes

Sharpe ratio (also known as reward-to-variability ratio) is a widely-used metric in finance, which measures the additional return at the cost of per unit of increased risk (standard deviation of return). However, the optimization of Sharpe ratio in Markov decision processes (MDPs) is challenging, because there exist two difficulties hindering the application of dynamic programming. One is that dynamic programming does not work for fractional objectives, and the other is that dynamic programming is invalid for risk metrics. In this paper, we study the Sharpe ratio optimization in infinite-horizon MDPs, considering both the long-run average and discounted settings. We address the first challenge with the Dinkelbachs transform, which converts the Sharpe ratio objective to a mean-squared-variance (M2V) objective. It is shown that the M2V optimization and the original Sharpe ratio optimization share the same optimal policy when the risk-sensitive parameter is equal to the optimal Sharpe ratio. For the second challenge, we develop an iterative algorithm to solve the M2V optimization which is similar to a mean-variance optimization in MDPs. We iteratively solve the M2V problem and obtain the associated Sharpe ratio that is used to update the risk-sensitive parameter in the next iteration of M2V problems. We show that such a sequence of Sharpe ratios derived is monotonically increasing and converges to the optimal Sharpe ratio. For both average and discounted MDP settings, we develop a policy iteration procedure and prove its convergence to the optimum. Numerical experiments are conducted for validation. To the best of our knowledge, our approach is the first that solves the Sharpe ratio optimization in MDPs with dynamic programming type algorithms. We believe that the proposed algorithm can shed light on solving MDPs with other fractional objectives.

cs.AI↗

arXiv2025

Regular Tree Search for Simulation Optimization

Tackling simulation optimization problems with non-convex objective functions remains a fundamental challenge in operations research. In this paper, we propose a class of random search algorithms, called Regular Tree Search, which integrates adaptive sampling with recursive partitioning of the search space. The algorithm concentrates simulations on increasingly promising regions by iteratively refining a tree structure. A tree search strategy guides sampling decisions, while partitioning is triggered when the number of samples in a leaf node exceeds a threshold that depends on its depth. Furthermore, a specific tree search strategy, Upper Confidence Bounds applied to Trees (UCT), is employed in the Regular Tree Search. We prove global convergence under sub-Gaussian noise, based on assumptions involving the optimality gap, without requiring continuity of the objective function. Numerical experiments confirm that the algorithm reliably identifies the global optimum and provides accurate estimates of its objective value.

math.OC↗

arXiv2025

Enhanced Derivative-Free Optimization Using Adaptive Correlation-Induced Finite Difference Estimators

Gradient-based methods are well-suited for derivative-free optimization (DFO), where finite-difference (FD) estimates are commonly used as gradient surrogates. Traditional stochastic approximation methods, such as Kiefer-Wolfowitz (KW) and simultaneous perturbation stochastic approximation (SPSA), typically utilize only two samples per iteration, resulting in imprecise gradient estimates and necessitating diminishing step sizes for convergence. In this paper, we first explore an efficient FD estimate, referred to as correlation-induced FD estimate, which is a batch-based estimate. Then, we propose an adaptive sampling strategy that dynamically determines the batch size at each iteration. By combining these two components, we develop an algorithm designed to enhance DFO in terms of both gradient estimation efficiency and sample efficiency. Furthermore, we establish the consistency of our proposed algorithm and demonstrate that, despite using a batch of samples per iteration, it achieves the same convergence rate as the KW and SPSA methods. Additionally, we propose a novel stochastic line search technique to adaptively tune the step size in practice. Finally, comprehensive numerical experiments confirm the superior empirical performance of the proposed algorithm.

math.OC↗

arXiv2024

A Correlation-induced Finite Difference Estimator

Finite difference (FD) approximation is a classic approach to stochastic gradient estimation when only noisy function realizations are available. In this paper, we first provide a sample-driven method via the bootstrap technique to estimate the optimal perturbation, and then propose an efficient FD estimator based on correlated samples at the estimated optimal perturbation. Furthermore, theoretical analyses of both the perturbation estimator and the FD estimator reveal that, {\it surprisingly}, the correlation enables the proposed FD estimator to achieve a reduction in variance and, in some cases, a decrease in bias compared to the traditional optimal FD estimator. Numerical results confirm the efficiency of our estimators and align well with the theory presented, especially in scenarios with small sample sizes. Finally, we apply the estimator to solve derivative-free optimization (DFO) problems, and numerical studies show that DFO problems with 100 dimensions can be effectively solved.

stat.ME↗

arXiv2022

Sample Recycling for Nested Simulation with Application in Portfolio Risk Measurement

Nested simulation is a natural approach to tackle nested estimation problems in operations research and financial engineering. The outer-level simulation generates outer scenarios and the inner-level simulations are run in each outer scenario to estimate the corresponding conditional expectation. The resulting sample of conditional expectations is then used to estimate different risk measures of interest. Despite its flexibility, nested simulation is notorious for its heavy computational burden. We introduce a novel simulation procedure that reuses inner simulation outputs to improve efficiency and accuracy in solving nested estimation problems. We analyze the convergence rates of the bias, variance, and MSE of the resulting estimator. In addition, central limit theorems and variance estimators are presented, which lead to asymptotically valid confidence intervals for the nested risk measure of interest. We conduct numerical studies on two financial risk measurement problems. Our numerical studies show consistent results with the asymptotic analysis and show that the proposed approach outperforms the standard nested simulation and a state-of-art regression approach for nested estimation problems.

q-fin.RM↗

arXiv2016

Conditional Monte Carlo: A Change-of-Variables Approach

Conditional Monte Carlo (CMC) has been widely used for sensitivity estimation with discontinuous integrands as a standard simulation technique. A major limitation of using CMC in this context is that finding conditioning variables to ensure continuity and tractability of the resulting conditional expectation is often problem dependent and may be difficult. In this paper, we attempt to circumvent this difficulty by proposing a change-of-variables approach to CMC, leading to efficient sensitivity estimators under mild conditions that are satisfied by a wide class of discontinuous integrands. These estimators do not rely on the structure of the simulation models and are less problem dependent. The value of the proposed approach is exemplified through applications in sensitivity estimation for financial options and gradient estimation of chance-constrained optimization problems.

math.PR↗