In the last few decades, Machine Learning (ML) has achieved significant success across domains ranging from healthcare, sustainability, and the social sciences, to criminal justice and finance. But its deployment in increasingly sophisticated, critical, and sensitive areas affecting individuals, the groups they belong to, and society as a whole raises critical concerns around fairness, transparency, robustness, and privacy, among others. As the complexity and scale of ML systems and of the settings in which they are deployed grow, so does the need for responsible ML methods that address these challenges while providing guaranteed performance in deployment. Mixed-integer optimization (MIO) offers a powerful framework for embedding responsible ML considerations directly into the learning process while maintaining performance. For example, it enables learning of inherently transparent models that can conveniently incorporate fairness or other domain specific constraints. This tutorial paper provides an accessible and comprehensive introduction to this topic discussing both theoretical and practical aspects. It outlines some of the core principles of responsible ML, their importance in applications, and the practical utility of MIO for building ML models that align with these principles. Through examples and mathematical formulations, it illustrates practical strategies and available tools for efficiently solving MIO problems for responsible ML. It concludes with a discussion on current limitations and open research questions, providing suggestions for future work.

We consider the problem of learning classification trees that are robust to distribution shifts between training and testing/deployment data. This problem arises frequently in high stakes settings such as public health and social work where data is often collected using self-reported surveys which are highly sensitive to e.g., the framing of the questions, the time when and place where the survey is conducted, and the level of comfort the interviewee has in sharing information with the interviewer. We propose a method for learning optimal robust classification trees based on mixed-integer robust optimization technology. In particular, we demonstrate that the problem of learning an optimal robust tree can be cast as a single-stage mixed-integer robust optimization problem with a highly nonlinear and discontinuous objective. We reformulate this problem equivalently as a two-stage linear robust optimization problem for which we devise a tailored solution procedure based on constraint generation. We evaluate the performance of our approach on numerous publicly available datasets, and compare the performance to a regularized, non-robust optimal tree. We show an increase of up to 12.48% in worst-case accuracy and of up to 4.85% in average-case accuracy across several datasets and distribution shifts from using our robust solution in comparison to the non-robust one.

Decision trees are among the most popular machine learning models and are used routinely in applications ranging from revenue management and medicine to bioinformatics. In this paper, we consider the problem of learning optimal binary classification trees with univariate splits. Literature on the topic has burgeoned in recent years, motivated both by the empirical suboptimality of heuristic approaches and the tremendous improvements in mixed-integer optimization (MIO) technology. Yet, existing MIO-based approaches from the literature do not leverage the power of MIO to its full extent: they rely on weak formulations, resulting in slow convergence and large optimality gaps. To fill this gap in the literature, we propose an intuitive flow-based MIO formulation for learning optimal binary classification trees. Our formulation can accommodate side constraints to enable the design of interpretable and fair decision trees. Moreover, we show that our formulation has a stronger linear optimization relaxation than existing methods in the case of binary data. We exploit the decomposable structure of our formulation and max-flow/min-cut duality to derive a Benders' decomposition method to speed-up computation. We propose a tailored procedure for solving each decomposed subproblem that provably generates facets of the feasible set of the MIO as constraints to add to the main problem. We conduct extensive computational experiments on standard benchmark datasets on which we show that our proposed approaches are 29 times faster than state-of-the-art MIO-based techniques and improve out-of-sample performance by up to 8%.

We consider the problem faced by a recommender system which seeks to offer a user with unknown preferences an item. Before making a recommendation, the system has the opportunity to elicit the user's preferences by making queries. Each query corresponds to a pairwise comparison between items. We take the point of view of either a risk averse or regret averse recommender system which only possess set-based information on the user utility function. We investigate: a) an offline elicitation setting, where all queries are made at once, and b) an online elicitation setting, where queries are selected sequentially over time. We propose exact robust optimization formulations of these problems which integrate the elicitation and recommendation phases and study the complexity of these problems. For the offline case, where the problem takes the form of a two-stage robust optimization problem with decision-dependent information discovery, we provide an enumeration-based algorithm and also an equivalent reformulation in the form of a mixed-binary linear program which we solve via column-and-constraint generation. For the online setting, where the problem takes the form of a multi-stage robust optimization problem with decision-dependent information discovery, we propose a conservative solution approach. We evaluate the performance of our methods on both synthetic data and real data from the Homeless Management Information System. We simulate elicitation of the preferences of policy-makers in terms of characteristics of housing allocation policies to better match individuals experiencing homelessness to scarce housing resources. Our framework is shown to outperform the state-of-the-art techniques from the literature.

According to the report, suicide is among the top 20 leading causes of death worldwide. Over the years, Artificial Intelligence (AI) tools have been used to fill gaps in mental health care: be it the diagnosis or detection of the early signs of mental health issues. Now, researchers at the University of South Carolina's Viterbi School of Engineering (USC's VSE) have developed an algorithm that can identify individuals in real-life social groups who can be trained as gatekeepers to spot suicidal tendencies. "Gatekeeper training" is an intervention training method approved by WHO. A suicide prevention gatekeeper can be any community member.

In a bid to help mitigate the risk of suicide especially among the homeless youth, a team of researchers at University of California (USC) has turned their focus towards Artificial Intelligence (AI). Phebe Vayanos, an associate director at USC's Center for Artificial Intelligence in Society (CAIS), and her team have been working over the last couple of years to design an algorithm capable of identifying who in a given real-life social group would be the best persons to be trained as "gatekeepers" capable of identifying warning signs of suicide and how to respond. "Our idea was to leverage real-life social network information to build a support network of strategically positioned individuals that can'watch-out' for their friends and refer them to help as needed," Vayanos said. Vayanos and study's lead author Aida Rahmattalabi investigated the potential of social connections such as friends, relatives and acquaintances to help mitigate the risk of suicide. "We want to ensure that a maximum number of people are being watched out for, taking into account resource limitations and uncertainties of open world deployment," Vayanos said.

According to the CDC, the suicide rate for individuals 10-24 years old has increased 56% between 2007 and 2017. In comparison to the general population, more than half of people experiencing homelessness have had thoughts of suicide or have attempted suicide, the National Health Care for the Homeless Council reported. Phebe Vayanos, assistant professor of Industrial and Systems Engineering and Computer Science at the USC Viterbi School of Engineering has been enlisting the help of a powerful ally -artificial intelligence- to help mitigate the risk of suicide. In this research, we wanted to find ways to mitigate suicidal ideation and death among youth. Our idea was to leverage real-life social network information to build a support network of strategically positioned individuals that can'watch-out' for their friends and refer them to help as needed." Vayanos, an associate director at USC's Center for Artificial Intelligence in Society (CAIS), and her team have been working over the last couple of years to design an algorithm capable of identifying who in a given real-life social group would be the best persons to be trained as "gatekeepers" capable of identifying warning signs of suicide and how to respond. Vayanos and Ph.D. candidate Aida Rahmattalabi, the lead author of the study "Exploring Algorithmic Fairness in Robust Graph Covering Problems," investigated the potential of social connections such as friends, relatives, and acquaintances to help mitigate the risk of suicide. Their paper will be presented at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS) this week. "We want to ensure that a maximum number of people are being watched out for, taking into account resource limitations and uncertainties of open world deployment.

According to the CDC, the suicide rate for individuals 10-24 years old has increased 56% between 2007 and 2017. In comparison to the general population, more than half of people experiencing homelessness have had thoughts of suicide or have attempted suicide, the National Health Care for the Homeless Council reported. Phebe Vayanos, assistant professor of Industrial and Systems Engineering and Computer Science at the USC Viterbi School of Engineering has been enlisting the help of a powerful ally--artificial intelligence--to help mitigate the risk of suicide. "In this research, we wanted to find ways to mitigate suicidal ideation and death among youth. Our idea was to leverage real-life social network information to build a support network of strategically positioned individuals that can'watch-out' for their friends and refer them to help as needed," Vayanos said.

According to the CDC, the suicide rate for individuals 10-24 years old has increased 56% between 2007 and 2017. In comparison to the general population, more than half of people experiencing homelessness have had thoughts of suicide or have attempted suicide, the National Health Care for the Homeless Council reported. Phebe Vayanos, assistant professor of Industrial and Systems Engineering and Computer Science at the USC Viterbi School of Engineering has been enlisting the help of a powerful ally -artificial intelligence- to help mitigate the risk of suicide. "In this research, we wanted to find ways to mitigate suicidal ideation and death among youth. Our idea was to leverage real-life social network information to build a support network of strategically positioned individuals that can'watch-out' for their friends and refer them to help as needed," Vayanos said.