Utility preference robust optimization (PRO) has recently been proposed to deal with optimal decision making problems where the decision maker's (DM) preference over gains and losses is ambiguous. In this paper, we take a step further to investigate the case that the DM's preference is not only ambiguous but also potentially inconsistent or even displaying some kind of randomness. We propose a distributionally preference robust optimization (DPRO) approach where the DM's preference is represented by a random utility function and the ambiguity is described by a set of probability distributions of the random utility. An obvious advantage of the new DPRO model is that it no longer concerns the DM's preference inconsistency. In the case when the random utility functions are of piecewise linear structure, we propose two statistical methods for constructing the ambiguity set: an ellipsoidal method and a bootstrap method both of which are fundamentally based on the idea of confidence region with the sample mean of the random parameters, and demonstrate how the resulting DPRO can be solved by a cutting surface algorithm and an MISOCP respectively. We also show how the DPRO models with general random utility functions may be approximated by those with piecewise linear random utility functions. Finally, we apply the proposed DPRO model in car manufacturing and facility location planning and show how the random samples may be extracted by multinomial logit method and conjoint analysis/machine learning. The paper is the first attempt to use distributionally robust optimization methods for PRO.
This paper introduces the distributionally robust random utility model (DRO-RUM), which allows the preference shock (unobserved heterogeneity) distribution to be misspecified or unknown. We make three contributions using tools from the literature on robust optimization. First, by exploiting the notion of distributionally robust social surplus function, we show that the DRO-RUM endogenously generates a shock distributionthat incorporates a correlation between the utilities of the different alternatives. Second, we show that the gradient of the distributionally robust social surplus yields the c…
In this paper, we consider a multi-attribute decision making problem where the decision maker's (DM's) objective is to maximize the expected utility of outcomes but the true utility function which captures the DM's risk preference is ambiguous. We propose a maximin multi-attribute utility preference robust optimization (UPRO) model where the optimal decision is based on the worst-case utility function in an ambiguity set of plausible utility functions constructed using partially available information such as the DM's specific preferences between some lotteries. Specifically, we consider a UPRO…
On the Foundation of Distributionally Robust Reinforcement Learning
Department of Industrial and Systems Engineering, University of Southern California（工业与系统工程系，南加州大学）；Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology（工业工程与决策分析，香港科技大学）；Management Science and Engineering, Stanford University（管理科学与工程，斯坦福大学）；Stern School of Business, New York University（斯特恩商学院，纽约大学）
Conditional Value at Risk (CVaR) is widely used to account for the preferences of a risk-averse agent in the extreme loss scenarios. To study the effectiveness of randomization in interdiction games with an interdictor that is both risk and ambiguity averse, we introduce a distributionally robust network interdiction game where the interdictor randomizes over the feasible interdiction plans in order to minimize the worst-case CVaR of the flow with respect to both the unknown distribution of the capacity of the arcs and his mixed strategy over interdicted arcs. The flow player, on the contrary,…
We consider black-box global optimization of time-consuming-to-evaluate functions on behalf of a decision-maker (DM) whose preferences must be learned. Each feasible design is associated with a time-consuming-to-evaluate vector of attributes and each vector of attributes is assigned a utility by the DM's utility function, which may be learned approximately using preferences expressed over pairs of attribute vectors. Past work has used a point estimate of this utility function as if it were error-free within single-objective optimization. However, utility estimation errors may yield a poor sugg…
Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback
Department of Statistics and Operations Research, University of North Carolina（统计与运筹学系，北卡罗来纳大学）；Imperial Business School, Imperial College London（帝国理工学院伦敦商学院）；Department of Management Science and Engineering, Stanford University（管理科学与工程系，斯坦福大学）
Decision maker's preferences are often captured by some choice functions which are used to rank prospects. In this paper, we consider ambiguity in choice functions over a multi-attribute prospect space. Our main result is a robust preference model where the optimal decision is based on the worst-case choice function from an ambiguity set constructed through preference elicitation with pairwise comparisons of prospects. Differing from existing works in the area, our focus is on quasi-concave choice functions rather than concave functions and this enables us to cover a wide range of utility/risk…
This paper is dedicated to a cautious learning methodology for predicting preferences between alternatives characterized by binary attributes (formally, each alternative is seen as a subset of attributes). By "cautious", we mean that the model learned to represent the multi-attribute preferences is general enough to be compatible with any strict weak order on the alternatives, and that we allow ourselves not to predict some preferences if the data collected are not compatible with a reliable prediction. A predicted preference will be considered reliable if all the simplest models (following Oc…
In data-driven inverse optimization an observer aims to learn the preferences of an agent who solves a parametric optimization problem depending on an exogenous signal. Thus, the observer seeks the agent's objective function that best explains a historical sequence of signals and corresponding optimal actions. We focus here on situations where the observer has imperfect information, that is, where the agent's true objective function is not contained in the search space of candidate objectives, where the agent suffers from bounded rationality or implementation errors, or where the observed sign…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Stanford University（斯坦福大学）
We propose a distributionally robust classification model with a fairness constraint that encourages the classifier to be fair in view of the equality of opportunity criterion. We use a type-$\infty$ Wasserstein ambiguity set centered at the empirical distribution to model distributional uncertainty and derive a conservative reformulation for the worst-case equal opportunity unfairness measure. We establish that the model is equivalent to a mixed binary optimization problem, which can be solved by standard off-the-shelf solvers. To improve scalability, we further propose a convex, hinge-loss-b…
Traditional network models encapsulate travel behavior among all origin-destination pairs based on a simplified and generic utility function. Typically, the utility function consists of travel time solely and its coefficients are equated to estimates obtained from stated preference data. While this modeling strategy is reasonable, the inherent sampling bias in individual-level data may be further amplified over network flow aggregation, leading to inaccurate flow estimates. This data must be collected from surveys or travel diaries, which may be labor intensive, costly and limited to a small t…
