Optimal counterfactual explanations for k-Nearest Neighbors using Mathematical Optimization and Constraint Programming

\(\) Within the topic of explainable AI, counterfactual explanations to classifiers have received significant recent attention. We study counterfactual explanations that try to explain why a data point received an undesirable classification by providing the closest data point that would have received a desirable one. Within the context of one the simplest and most popular … Read more

It’s All in the Mix: Wasserstein Machine Learning with Mixed Features

Citation Belbasi R., Selvi A., Wiesemann W. (December 2023) It’s all in the mix: Wasserstein machine learning with mixed features. Preprint. Article Download View It's All in the Mix: Wasserstein Machine Learning with Mixed Features

Data-driven Stochastic Vehicle Routing Problems with Deadline Assignment

In this paper, we study a data-driven stochastic vehicle routing problem (VRP) with deadlines and endogenous uncertainty, where the travel time depends on the routing decisions, which is motivated by a real-world food delivery problem. We use the non-parametric approaches, including k-nearest neighbor (kNN) and kernel density estimation, to estimate the decision-dependent probability distribution of … Read more

Data-Driven Counterfactual Optimization For Personalized Clinical Decision-Making

Chronic diseases have a significant impact on global mortality rates and healthcare costs. Notably, machine learning-based clinical assessment tools are becoming increasingly popular for informing treatment targets for high-risk patients with chronic diseases. However, using these tools alone, it is challenging to identify personalized treatment targets that lower the risks of adverse outcomes to a … Read more

Finding Regions of Counterfactual Explanations via Robust Optimization

Counterfactual explanations play an important role in detecting bias and improving the explainability of data-driven classification models. A counterfactual explanation (CE) is a minimal perturbed data point for which the decision of the model changes. Most of the existing methods can only provide one CE, which may not be achievable for the user. In this … Read more

The Online Shortest Path Problem: Learning Travel Times Using A Multi-Armed Bandit Framework

In the age of e-commerce, many logistic companies must operate in large road networks without accurate knowledge of travel times for their specific fleet of vehicles. Moreover, millions of dollars are spent on routing services that do not accurately capture the specific characteristics of the companies’ drivers and the types of vehicles they must use. … Read more

Data-driven Prediction of Relevant Scenarios for Robust Combinatorial Optimization

We study iterative methods for (two-stage) robust combinatorial optimization problems with discrete uncertainty. We propose a machine-learning-based heuristic to determine starting scenarios that provide strong lower bounds. To this end, we design dimension-independent features and train a Random Forest Classifier on small-dimensional instances. Experiments show that our method improves the solution process for larger instances … Read more

Learning to Accelerate the Global Optimization of Quadratically-Constrained Quadratic Programs

We learn optimal instance-specific heuristics for the global minimization of nonconvex quadratically-constrained quadratic programs (QCQPs). Specifically, we consider partitioning-based mixed-integer programming relaxations for nonconvex QCQPs and propose the novel problem of strong partitioning to optimally partition variable domains without sacrificing global optimality. We design a local optimization method for solving this challenging max-min strong partitioning … Read more

A mixed-integer exponential cone programming formulation for feature subset selection in logistic regression

Logistic regression is one of the widely-used classification tools to construct prediction models. For datasets with a large number of features, feature subset selection methods are considered to obtain accurate and interpretable prediction models, in which irrelevant and redundant features are removed. In this paper, we address the problem of feature subset selection in logistic … Read more

Deep learning and hyperparameter optimization for assessing one’s eligibility for a subcutaneous implantable cardioverter-defibrillator

In cardiology, it is standard for patients suffering from ventricular arrhythmias (the leading cause of sudden cardiac death) belonging to high risk populations to be treated using Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs). S-ICDs carry a risk of so-called T Wave Over Sensing (TWOS), which can lead to inappropriate shocks with an inherent health risk. For this … Read more