Search

Online linear programming (OLP) has gained significant attention from both researchers and practitioners due to its extensive applications, such as online auction, network revenue management and advertising. Existing OLP algorithms fall into two categories: LP-based algorithms and LP-free algorithms. The former one typically guarantees better performance, even offering a constant regret, but requires solving a large number of LPs, which could be computationally expensive. In contrast, LP-free algorithm only requires first-order computations but induces a worse performance, lacking a constant regret bound. In this work, we study the case where the inputs are drawn from an unknown finite-support distribution, and bridge the gap between these two extremes by proposing an algorithm that achieves a constant regret while solving LPs only $O(\log\log T)$ times over the time horizon $T$. Moreover, when we are allowed to solve LPs only $M$ times, we propose an algorithm that can guarantee an $O\left(T^{(1/2+\epsilon)^{M-1}}\right)$ regret. Furthermore, when the arrival probabilities are known at the beginning, our algorithm can guarantee a constant regret by solving LPs $O(\log\log T)$ times, and an $O\left(T^{(1/2+\epsilon)^{M}}\right)$ regret by solving LPs only $M$ times. Numerical experiments are conducted to demonstrate the efficiency of the proposed algorithms., Comment: 35 pages, 7 figures

Optimization modeling and solving play a critical role in the application of Operations Research (OR) tools to address real-world problems, yet they pose challenges and require extensive expertise from OR experts. With the advent of large language models (LLMs), new opportunities have emerged to streamline and automate these tasks. However, current research predominantly relies on closed-source LLMs such as GPT-4, along with extensive prompt engineering techniques. This reliance stems from the scarcity of high-quality training datasets for optimization modeling, resulting in elevated costs, prolonged processing times, and privacy concerns. To address these challenges, our work is the first to propose a viable path for training open-source LLMs that are capable of optimization modeling as well as developing and executing solver codes, eventually leading to a superior ability for automating optimization modeling and solving. Particularly, we introduce a semi-automated data synthesis framework designed for optimization modeling issues, named OR-Instruct. This framework merges the training data requirements of large models with the unique characteristics of optimization modeling problems, and allows for customizable enhancements tailored to specific scenarios or modeling types. To evaluate the performance of our proposed framework, we present the IndustryOR benchmark, the inaugural industrial standard for evaluating LLMs in solving practical OR problems. Utilizing data synthesized through OR-Instruct, we train various open-source LLMs with a capacity of 7 billion parameters (dubbed ORLMs). The resulting model demonstrates significantly enhanced optimization modeling capabilities, achieving state-of-the-art performance across the NL4OPT, MAMO, and IndustryOR benchmarks. Our code and data are available at \url{https://github.com/Cardinal-Operations/ORLM}., Comment: Work in progress

Visual Cryptography Schemes (VCS) based on the "XOR" operation (XVCS) exhibit significantly smaller pixel expansion and higher contrast compared to those based on the "OR" operation. Moreover, the "XOR" operation appears to possess superior qualities, as it effectively operates within a binary field, while the "OR" operation merely functions as a ring with identity. Despite these remarkable attributes, our understanding of XVCS remains limited. Especially, we have done little about the noise in the reconstructed image up to now. In this paper, we introduce a novel concept called Static XVCS (SXVCS), which completely eliminates the noise in the reconstructed image. We also demonstrate that the equivalent condition for perfect white pixel reconstruction is simply the existence of SXVCS. For its application, we naturally propose an efficient method for determining the existence of XVCS with perfect white pixel reconstruction. Furthermore, we apply our theorem to $(2,n)$-XVCS and achieve the optimal state of $(2,n)$-XVCS., Comment: 29 pages

In this paper, we study a bivariate distributionally robust optimization problem with mean-covariance ambiguity set and half-space support. Under a conventional type of objective function widely adopted in inventory management, option pricing, and portfolio selection, we obtain closed-form tight bounds of the inner problem in six different cases. Through a primal-dual approach, we identify the optimal distributions in each case. As an application in inventory control, we first derive the optimal order quantity and the corresponding worst-case distribution, extending the existing results in the literature. Moreover, we show that under the distributionally robust setting, a centralized inventory system does not necessarily reduce the optimal total inventory, which contradicts conventional wisdom. Furthermore, we identify two effects, a conventional pooling effect, and a novel shifting effect, the combination of which determines the benefit of incorporating the covariance information in the ambiguity set. Finally, we demonstrate through numerical experiments the importance of keeping the covariance information in the ambiguity set instead of compressing the information into one dimension.

Cardinal Optimizer is a high-performance mathematical programming solver for efficiently solving largescale optimization problem. This documentation provides basic introduction to the Cardinal Optimizer.

Prediction markets are long known for prediction accuracy. This study systematically explores the fundamental properties of prediction markets, addressing questions about their information aggregation process and the factors contributing to their remarkable efficacy. We propose a novel multivariate utility (MU) based mechanism that unifies several existing automated market-making schemes. Using this mechanism, we establish the convergence results for markets comprised of risk-averse traders who have heterogeneous beliefs and repeatedly interact with the market maker. We demonstrate that the resulting limiting wealth distribution aligns with the Pareto efficient frontier defined by the utilities of all market participants. With the help of this result, we establish analytical and numerical results for the limiting price in different market models. Specifically, we show that the limiting price converges to the geometric mean of agent beliefs in exponential utility-based markets. In risk-measure-based markets, we construct a family of risk measures that satisfy the convergence criteria and prove that the price can converge to a unique level represented by the weighted power mean of agent beliefs. In broader markets with Constant Relative Risk Aversion (CRRA) utilities, we reveal that the limiting price can be characterized by systems of equations that encapsulate agent beliefs, risk parameters, and wealth. Despite the potential impact of traders' trading sequences on the limiting price, we establish a price invariance result for markets with a large trader population. Using this result, we propose an efficient approximation scheme for the limiting price.

We analyze the optimal partition and assignment strategy for an uncapacitated FCFS queueing system with multiple types of customers. Each type of customers is associated with a certain arrival and service rate. The decision maker can partition the server into sub-queues, each with a smaller service capacity, and can route different types of customers to different sub-queues (deterministically or randomly). The objective is to minimize the overall expected waiting time. First, we show that by properly partitioning the queue, it is possible to reduce the expected waiting time of customers, and there exist a series of instances such that the reduction can be arbitrarily large. Then we consider four settings of this problem, depending on whether the partition is given (thus only assignment decision is to be made) or not and whether each type of customers can only be assigned to a unique queue or can be assigned to multiple queues in a probabilistic manner. When the partition is given, we show that this problem is NP-hard in general if each type of customers must be assigned to a unique queue. When the customers can be assigned to multiple queues in a probabilistic manner, we identify a structure of the optimal assignment and develop an efficient algorithm to find the optimal assignment. When the decision maker can also optimize the partition, we show that the optimal decision must be to segment customers deterministically based on their service rates, and to assign customers with consecutive service rates into the same queue. Efficient algorithms are also proposed in this case. Overall, our work is the first to comprehensively study the queue partition problem based on customer types, which has the potential to increase the efficiency of queueing system.

In this paper, we consider a new Multi-Armed Bandit (MAB) problem where arms are nodes in an unknown and possibly changing graph, and the agent (i) initiates random walks over the graph by pulling arms, (ii) observes the random walk trajectories, and (iii) receives rewards equal to the lengths of the walks. We provide a comprehensive understanding of this problem by studying both the stochastic and the adversarial setting. We show that this problem is not easier than a standard MAB in an information theoretical sense, although additional information is available through random walk trajectories. Behaviors of bandit algorithms on this problem are also studied., Comment: major revision

We present a probabilistic forecasting framework based on convolutional neural network for multiple related time series forecasting. The framework can be applied to estimate probability density under both parametric and non-parametric settings. More specifically, stacked residual blocks based on dilated causal convolutional nets are constructed to capture the temporal dependencies of the series. Combined with representation learning, our approach is able to learn complex patterns such as seasonality, holiday effects within and across series, and to leverage those patterns for more accurate forecasts, especially when historical data is sparse or unavailable. Extensive empirical studies are performed on several real-world datasets, including datasets from JD.com, China's largest online retailer. The results show that our framework outperforms other state-of-the-art methods in both accuracy and efficiency., Comment: 24 pages, 3 figures, 8 tables

Stochastic optimization finds a wide range of applications in operations research and management science. However, existing stochastic optimization techniques usually require the information of random samples (e.g., demands in the newsvendor problem) or the objective values at the sampled points (e.g., the lost sales cost), which might not be available in practice. In this paper, we consider a new setup for stochastic optimization, in which the decision maker has access to only comparative information between a random sample and two chosen decision points in each iteration. We propose a comparison-based algorithm (CBA) to solve such problems in one dimension with convex objective functions. Particularly, the CBA properly chooses the two points in each iteration and constructs an unbiased gradient estimate for the original problem. We show that the CBA achieves the same convergence rate as the optimal stochastic gradient methods (with the samples observed). We also consider extensions of our approach to multi-dimensional quadratic problems as well as problems with non-convex objective functions. Numerical experiments show that the CBA performs well in test problems.

In this paper, we consider a Markov chain choice model with single transition. In this model, customers arrive at each product with a certain probability. If the arrived product is unavailable, then the seller can recommend a subset of available products to the customer and the customer will purchase one of the recommended products or choose not to purchase with certain transition probabilities. The distinguishing features of the model are that the seller can control which products to recommend depending on the arrived product and that each customer either purchases a product or leaves the market after one transition. We study the assortment optimization problem under this model. Particularly, we show that this problem is generally NP-Hard even if each product could only transit to at most two products. Despite the complexity of the problem, we provide polynomial time algorithms for several special cases, such as when the transition probabilities are homogeneous with respect to the starting point, or when each product can only transit to one other product. We also provide a tight performance bound for revenue-ordered assortments. In addition, we propose a compact mixed integer program formulation that can solve this problem of large size. Through extensive numerical experiments, we show that the proposed algorithms can solve the problem efficiently and the obtained assortments could significantly improve the revenue of the seller than under the Markov chain choice model.

We introduce a parallel machine scheduling problem in which the processing times of jobs are not given in advance but are determined by a system of linear constraints. The objective is to minimize the makespan, i.e., the maximum job completion time among all feasible choices. This novel problem is motivated by various real-world application scenarios. We discuss the computational complexity and algorithms for various settings of this problem. In particular, we show that if there is only one machine with an arbitrary number of linear constraints, or there is an arbitrary number of machines with no more than two linear constraints, or both the number of machines and the number of linear constraints are fixed constants, then the problem is polynomial-time solvable via solving a series of linear programming problems. If both the number of machines and the number of constraints are inputs of the problem instance, then the problem is NP-Hard. We further propose several approximation algorithms for the latter case., Comment: 21 pages

Based on the observation that many existing discrete choice models admit a welfare function of utilities whose gradient gives the choice probability vector, we propose a new representation of discrete choice model which we call the welfare-based choice model. The welfare-based choice model is meaningful on its own by providing a new way of constructing choice models. More importantly, it provides great analysis convenience for establishing connections among existing choice models. We prove by using convex analysis theory, that the welfare-based choice model is equivalent to the representative agent choice model and the semi-parametric choice model, establishing the equivalence of the latter two. We show that these three models are all strictly more general than the random utility model, while when there are only two alternatives, those four models are equivalent. In particular, we show that the distinction between the welfare-based choice model and the random utility model lies in the requirement of the higher-order derivatives of the welfare function. We then define a new concept in choice models: substitutability/complementarity between alternatives. We show that the random utility model only allows substitutability between different alternatives; while the welfare-based choice model allows flexible substitutability/complementarity patterns. We argue that such flexibility could be desirable in capturing certain practical choice patterns and expanding the scope of discrete choice models. Examples are given of new choice models proposed under our framework.

In this paper, we present a unified framework for decision making under uncertainty. Our framework is based on the composite of two risk measures, where the inner risk measure accounts for the risk of decision given the exact distribution of uncertain model parameters, and the outer risk measure quantifies the risk that occurs when estimating the parameters of distribution. We show that the model is tractable under mild conditions. The framework is a generalization of several existing models, including stochastic programming, robust optimization, distributionally robust optimization, etc. Using this framework, we study a few new models which imply probabilistic guarantees for solutions and yield less conservative results comparing to traditional models. Numerical experiments are performed on portfolio selection problems to demonstrate the strength of our models.

Consider the regularized sparse minimization problem, which involves empirical sums of loss functions for $n$ data points (each of dimension $d$) and a nonconvex sparsity penalty. We prove that finding an $\mathcal{O}(n^{c_1}d^{c_2})$-optimal solution to the regularized sparse optimization problem is strongly NP-hard for any $c_1, c_2\in [0,1)$ such that $c_1+c_2<1$. The result applies to a broad class of loss functions and sparse penalty functions. It suggests that one cannot even approximately solve the sparse optimization problem in polynomial time, unless P $=$ NP.

This paper discusses the fixed-hub single allocation problem (FHSAP). In this problem, a network consists of hub nodes and terminal nodes. Hubs are fixed and fully connected; each terminal node is connected to a single hub which routes all its traffic. The goal is to minimize the cost of routing the traffic in the network. In this paper, we propose a linear programming (LP)-based rounding algorithm. The algorithm is based on two ideas. First, we modify the LP relaxation formulation introduced in Ernst and Krishnamoorthy (1996, 1999) by incorporating a set of validity constraints. Then, after obtaining a fractional solution to the LP relaxation, we make use of a geometric rounding algorithm to obtain an integral solution. We show that by incorporating the validity constraints, the strengthened LP often provides much tighter upper bounds than the previous methods with a little more computational effort, and the solution obtained often has a much smaller gap with the optimal solution. We also formulate a robust version of the FHSAP and show that it can guard against data uncertainty with little cost.

We consider optimal decision-making problems in an uncertain environment. In particular, we consider the case in which the distribution of the input is unknown, yet there is abundant historical data drawn from the distribution. In this paper, we propose a new type of distributionally robust optimization model called the likelihood robust optimization (LRO) model for this class of problems. In contrast to previous work on distributionally robust optimization that focuses on certain parameters (e.g., mean, variance, etc.) of the input distribution, we exploit the historical data and define the accessible distribution set to contain only those distributions that make the observed data achieve a certain level of likelihood. Then we formulate the targeting problem as one of optimizing the expected value of the objective function under the worst-case distribution in that set. Our model avoids the over-conservativeness of some prior robust approaches by ruling out unrealistic distributions while maintaining robustness of the solution for any statistically likely outcomes. We present statistical analyses of our model using Bayesian statistics and empirical likelihood theory. Specifically, we prove the asymptotic behavior of our distribution set and establish the relationship between our model and other distributionally robust models. To test the performance of our model, we apply it to the newsvendor problem and the portfolio selection problem. The test results show that the solutions of our model indeed have desirable performance.