Problems encountered in addressing these challenges usually involve allocating scarce intervention resources in messy real-world environments informed by data that is potentially biased, noisy, or scarce while taking into account complex, sometimes conflicting, objectives and constraints. Examples include deciding how to allocate scarce housing resources to people experiencing homelessness, personalizing substance use prevention interventions, designing social network-based interventions for suicide prevention, deciding where to conserve habitat to protect biodiversity, and strategically strengthening community resilience to mitigate landslide risks.

My overarching career goal is to define, grow, and strengthen the field of OR and AI for Society through my research, teaching, and service activities. In particular, the objective of my research program is to support this goal through important research contributions that:

1. significantly advance the underlying mathematical and computational techniques, which span integer, stochastic, and robust optimization, and their interface with machine learning, causal inference, and economics to enable the design of predictive and prescriptive models that are suitable to deploy in high-stakes settings; and

2. successfully apply the methods and tools created to make a positive impact on society, and in particular on underserved and marginalized communities.

To meet my research goal, I form partnerships with domain experts, community partners, and policy-makers, facilitated by my position as Associate Director of the USC Center for AI in Society (CAIS) which drives research in AI and OR to tackle important societal problems. These collaborations help me identify important research questions in OR and AI which, if successfully addressed, can make a significant impact to improve the health and well-being of people and the planet. These partnerships also ensure that the methods and tools we develop in my lab translate to direct benefits through deployment.

The knowledge and tools we create in this fashion are directly driven by their potential use in high-stakes domains which are permeated by uncertainty and preexisting biases. Thus, they need to be robust, to perform as planned and intended, interpretable, thus easy to scrutinize and implement, and fair, to avoid introducing or perpetrating biases. Designing predictive and prescriptive models with these characteristics from biased, noisy, or scarce data gives rise to hard, often combinatorial, constrained optimization problems affected by uncertainty. To solve them, I devise models, algorithms, and approximation schemes that fall in the areas of data-driven stochastic and robust optimization and integer programming. Notably, my models often integrate in novel and impactful ways methods from optimization and causal inference or statistics to deal with noise, distribution shifts, estimation errors, and biases.

These advances were inspired by problems identified through the partnerships I have formed. Notably, many of them are motivated by problems encountered in my collaboration with LAHSA, the Los Angeles Homeless Services Authority, in our joint efforts to mitigate homelessness in LA. Others were identified through discussions with Panthera, an organization dedicated to preserving wild cats, in our collaboration aimed to save the jaguars in Central and South America; or with RAND and the Sitka Sound Science Center in our efforts to mitigate landslide risk in the town of Sitka, Alaska. They are also motivated by discussions with the Massachusetts General Hospital (MGH), for which I provided decision-support tools for patients on the deceased donor kidney transplant waitlist; the LAC+USC Medical Center, which I am helping with ethical dilemmas related to resource shortages in pandemics; the University of Denver, which will deploy our social network-based suicide prevention intervention; and, more recently, Chestnut Health Systems, which I am helping design personalized substance use prevention interventions.

My research is supported by a variety of sources, both internal and external to USC. Notably, my work on homelessness is supported, over time, by my NSF CAREER award, a gift from Schmidt Futures, a grant from the Conrad N. Hilton Foundation and the United Way of Greater LA Home for Good program, and a USC Zumberge Diversity & Inclusion grant. My work on conservation is supported by funds from the Microsoft Research AI for Earth program and an NSF Operations Engineering program grant. My work on suicide prevention is supported by a grant from the U.S. Army Research Labs and a gift from the Living to Love Another Day foundation. My work on landslide risk management is supported by funds from the NSF Smart & Connected Communities program. Finally, my research on Covid-19 resource allocation is supported by a USC Zumberge Special Solicitation grant.

1. Facts About Suicide. URL: https://www.cdc.gov/suicide/facts/index.html.

2. Grand Challenges for Social Work. URL: https://grandchallengesforsocialwork.org.

3. LAHSA CES Triage Tool Research & Refinement webpage. URL: https://www.lahsa.org/ documents?id=4370-ces-triage-tool-research-refinement.pdf.

4. Landslides 101. URL: https://www.usgs.gov/programs/landslide-hazards/landslides-101.

5. Too Many Donor Kidneys Are Discarded in U.S. Before Transplantation. URL:https://www.pennmedicine.org/news/news-releases/2020/december/ too-many-donor-kidneys-are-discarded-in-us-before-transplantation.

6. S Aghaei, M J Azizi, and P Vayanos. Learning optimal and fair decision trees for non- discriminative decision-making.In Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019.

7. S Aghaei, A Gómez, and P Vayanos. Strong optimal classification trees. Major revision at Operations Research, 2022. URL: https://arxiv.org/abs/2002.09142.

8. M J Azizi, P Vayanos, B Wilder, E Rice, and M Tambe. Designing fair, efficient, and in- terpretable policies for prioritizing homeless youth for housing resources. In Proceedings of the 15th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 2018.

9. C Bandi, N Trichakis, and P Vayanos. Robust multiclass queuing theory for wait time esti- mation in resource allocation systems. Management Science, 65(1):152–187, 2018.

10. Q Jin, A Georghiou, P Vayanos, and G Hanasusanto. Distributionally robust optimization with decision-dependentinformation discovery. In preparation for submission to INFORMS Journal on Computing, 2022.

11. N Jo, S Aghaei, J Benson, A Gómez, and P Vayanos. Learning optimal fair classication trees. Under review at second ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO’22), 2022. URL: https://arxiv.org/pdf/2201.09932.pdf.

12. N Jo, S Aghaei, A Gómez, and P Vayanos. Learning optimal prescriptive trees from observa- tional data. Major Revision at Management Science, short version appeared at 2022 AAAI Workshop on AI and Behavior Change, 2021. URL:https://arxiv.org/pdf/2108.13628. pdf.

13. N Jo, B Tang, K Dullerud, S Aghaei, E Rice, and P Vayanos. Evaluating fairness of contextual resource allocationsystems: metrics and impossibility results. In preparation for submission to 37th AAAI Conference on Artificial Intelligence, 2022.

14. C Johnston, S Blessenhohl, and P Vayanos. Preference Elicitation and Aggregation to Aid with Patient Triage during the COVID-19 Pandemic. In preparation for submission to Operations Research; short version appeared in International Conference on Machine Learning (ICML) Workshop on Participatory Approaches to Machine Learning, 2020.

15. N Justin, S Aghaei, A G´omez, and P Vayanos. Optimal robust classification trees. In prepa- ration for submission to Operations Research; short version appeared in AAAI Workshop on Adversarial Machine Learning and Beyond, 2021.

16. A Rahmattalabi, P Vayanos, K Dullerud, and E Rice. Learning resource allocation policies from observational data with an application to homeless services delivery. In 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT ’22), 2022.

17. A Rahmattalabi, P Vayanos, A Fulginiti, E Rice, B Wilder, A Yadav, and M Tambe. Exploring algorithmic fairness in robust graph covering problems. In Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS), 2019.

18. B Tang, C Koçyigit, and P Vayanos. Learning optimal policies for allocating housing to people experiencinghomelessness from data collected in deployment. In preparation for submission to Management Science, 2022.

19. United-Nations. Resolution adopted by the General Assembly on 6 July 2017, Work of the Statistical Commissionpertaining to the 2030 Agenda for Sustainable Development. 2017.

20. P Vayanos, A Georghiou, and H Yu. Robust optimization with decision-dependent information discovery. Major revisionat Management Science, 2019. URL: https://arxiv.org/pdf/ 2004.08490.pdf.

21. P Vayanos, Q Jin, and G Elissaios. ROC++: Robust Optimization in C++. Forthcoming at INFORMS Journal on Computing, 2022. URL: https://arxiv.org/pdf/2006.08741.pdf.

22. P Vayanos, Q Jin, and G Elissaios. ROCPP Version v2020.0140. INFORMS Journal on Computing, 2022.doi:10.5281/zenodo.6360996.

23. P Vayanos, D Kuhn, and B Rustem. Decision rules for information discovery in multi-stage stochastic programming. InProceedings of the 50th IEEE Conference on Decision and Control, pages 7368–7373, 2011.

24. P Vayanos, D Kuhn, and B Rustem. A constraint sampling approach for multi-stage robust optimization. Automatica, 48(3):459–471, 2012.

25. P Vayanos, W Wiesemann, and D Kuhn. Hedging electricity swing options in incomplete markets. In Proceedings of the 18th IFAC Wold Congress, pages 846–853, 2011.

26. P Vayanos, Y Ye, D McElfresh, J Dickerson, and E Rice. Robust active preference elicitation. Under second round ofreview at Management Science, 2021. URL: https://arxiv.org/pdf/ 2003.01899.pdf.

27. P Vossler, S Aghaei, N Justin, N Jo, A Gómez, and P Vayanos. ODTlearn package v0.1. URL: https://github.com/D3M-Research-Group/odtlearn.

28. P Vossler, S Aghaei, N Justin, N Jo, A Gómez, and P Vayanos. ODTlearn: a Python package for learning optimal decision trees. In preparation for submission to Journal of Machine Learning Research, 2022.

29. Y Ye, C Doehring, A Georghiou, P Vayanos, and H Robinson. Conserving biodiversity via ad- justable robust optimization. In preparation for submission to Management Science; short version appeared in Proc. of the 21st International Conference on Autonomous Agents and Mul- tiagent Systems (AAMAS 2022), Workshop on Autonomous Agents for Social Good (AASG), 2022.