State-of-the-art exact methods for solving vehicle routing problems rely on a dynamic program that enumerates the set of feasible routes and their distances. Using relaxations of the dynamic program improves these exact methods. This work is motivated by two observations. First, the dynamic program enumerates some routes with a suboptimal permutation of the locations. Second, … Read more
The Continuous-Time Service Network Design Problem (CTSNDP) arises in consolidation-based transportation systems, where shipments share paths in space and time to reduce cost. The CTSNDP determines minimum-cost transportation plans over a continuous-time horizon. To provide more consolidation opportunities and achieve further cost reductions, CTSNDP with Splittable Deliveries (SCTSNDP) allows each commodity to be divided into … Read more
This article introduces the Electric Vehicle Itinerary Planning with Activities (EV-IPA) problem, which jointly optimizes vehicle routing, parallel activity scheduling, non-linear charging decisions, and time-window constraints. This tight coupling is increasingly relevant as conversational in-car assistants let drivers negotiate itineraries in natural language. However, directly embedding continuous, non-linear state-of-charge dynamics into a discrete decision space … Read more
We propose GenericILS, a general-purpose heuristic framework for generating high-quality upper bounds for Vehicle Routing Problems whose pricing subproblems are modeled, in column-generation-based exact algorithms, as resource-constrained shortest path problems described through Resource Extension Functions (REFs), the standard device for encoding constraints in branch-and-price algorithms. GenericILS reuses REFs implemented for the exact method, without a … Read more
We propose robust and distributionally robust formulations of the risk budgeting problem under the mean absolute deviation (MAD) risk measure. The proposed models address uncertainty in asset returns and their distribution while allocating portfolio risk according to prescribed risk budgets. We first develop a robust model in which historical return observations are perturbed within a … Read more
Large language models improve test-time accuracy by generating multiple rollouts and aggregating these answers. As generating additional rollouts consumes more tokens, test-time compute faces a fundamental cost accuracy trade-off, naturally raising the question: given a fixed token budget, how to allocate the budget to maximize accuracy? Existing approaches typically adapt the number of rollouts for … Read more
Deep hedging learns trading policies from historical or simulated market trajectories, yet under nonstationarity these training paths may not represent future market conditions. We propose WRAP (Wasserstein-Reweighting Adversarial Perturbation), a drift-aware adversarial training framework derived from a two-budget distributionally robust optimization (DRO) formulation. The formulation is anchored to a weighted empirical reference distribution whose fixed … Read more
We propose a data-driven linear programming model to compute energy-optimal timetables for networks operating under communications-based train control (CBTC); the model was developed in collaboration with Hitachi Rail Canada, the largest provider of CBTC systems worldwide. Our model minimizes the network’s effective energy consumption, defined as the total traction energy consumed by the trains minus … Read more
This paper studies the single-machine problem of minimizing the weighted completion time variance (WCTV) and proposes a polynomially computable lower-bounding framework that generalizes the benchmark introduced by Nessah and Chu (2010). We first develop a generalized augmented-sequence decomposition that mathematically connects the weighted problem with the classical unweighted variance setting. Using this decomposition, we derive … Read more
We study the problem of learning revenue-maximizing bundle prices when customer valuations and market composition are unknown and the firm observes only customer choices. This problem is challenging because the number of bundle-price decisions grows exponentially with the number of items offered. We develop BLMP (Bundle Pricing via Learning the Market from Customer Preferences), a … Read more