University of Southern California
Research Group
Bryan Wilder


Bryan Wilder I am a fourth year PhD student in the Department of Computer Science at University of Southern California, advised by Milind Tambe. I work on optimization and machine learning for social impact with an emphasis on health, homelessness, and inequality. My algorithmic research spans the full pipeline from data to decisions. Among other topics, I've explored how to integrate combinatorial optimization problems into machine learning models, how to gather data to inform interventions, and how to find decisions that are robust to uncertainty. One product of this research is an algorithmically-driven intervention for preventing HIV spread among homeless youth that is currently being piloted by LA-area homeless centers. My work draws on close collaborations with NGOs, social workers, epidemiologists, and a range of other partners.

I coordinate the MD4SG Working Group on Global Perspectives on Inequality and co-organize the Computational Sustainability Online Graduate Seminar. I am supported by a National Science Foundation Graduate Research Fellowship.


CV [pdf]
bwilder@usc.edu


News
  • [February 2019]: I'm co-organizing a workshop at IJCAI 2019 on AI for Social Good! Please consider submitting.
  • [November 2018]: Two papers accepted at AAAI-19, including one on integrating learning and combinatorial optimization.
  • [September 2018]: Our HIV prevention project is a finalist for the INFORMS Doing Good with Good OR award. Come see the talk at INFORMS!
  • [July 2018]: Our paper on field-ready influence maximization algorithms was nominated for the best student paper award at AAMAS-18.
  • [June 2018]: I will be co-presenting (with Eugene Vorobeychik) a tutorial on "Algorithmic Social Intervention" at IJCAI 2018.
  • [Jan 2018]: 4 papers accepted at AAMAS-18.
  • [Nov 2018]: 4 papers accepted at AAAI-18.
  • [April 2017]: Our paper on deployed influence maximization was nominated for the best paper award at AAMAS-17.
Preprints
  • Jackson A. Killian, Bryan Wilder, Amit Sharma, Vinod Choudhary, Bistra Dilkina, Milind Tambe.
    Learning to Prescribe Interventions for Tuberculosis Patients using Digital Adherence Data. [arXiv].

  • Alan Tsang*, Bryan Wilder*, Eric Rice, Milind Tambe, Yair Zick.
    Group-Fairness in Influence Maximization. [arXiv].
    *Equal contribution.

  • Andrew Perrault, Bryan Wilder, Eric Ewing, Aditya Mate, Bistra Dilkina, Milind Tambe
    Decision-Focused Learning of Adversary Behavior in Security Games. [arXiv].
Conference Publications
  • Matthew Staib* Bryan Wilder*, Stefanie Jegelka.
    Distributionally Robust Submodular Maximization. [arXiv].
    AISTATS-19. To appear: International Conference on Artificial Intelligence and Statistics. 2019.
    *Equal contribution.

  • Bryan Wilder, Bistra Dilkina, Milind Tambe.
    Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization. [PDF] [arXiv][code][datasets].
    AAAI-19. To appear: AAAI Conference on Artificial Intelligence. 2019.

  • Bryan Wilder, Yevgeniy Vorobeychik.
    Defending Elections Against Malicious Spread of Misinformation. [PDF] [arXiv].
    AAAI-19. To appear: AAAI Conference on Artificial Intelligence. 2019.

  • Mohammad Javad Azizi, Phebe Vayanos, Bryan Wilder, Eric Rice, Milind Tambe.
    Designing Fair, Efficient, and Interpretable Policies for Prioritizing Homeless Youth for Housing Resources. [PDF]
    CPAIOR-18. International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research. 2018.
    Invited to Constraints journal fast track for outstanding papers

  • Bryan Wilder, Laura Onasch-Vera, Juliana Hudson, Jose Luna, Nicole Wilson, Robin Petering, Darlene Woo, Milind Tambe, Eric Rice.
    End-to-End Influence Maximization in the Field. [PDF]
    AAMAS-18. International Conference on Autonomous Agents and Multiagent Systems. 2018.
    Nominated for best student paper

  • Bryan Wilder, Han Ching Ou, Kayla de la Haye, Milind Tambe.
    Optimizing network structure for preventative health. [PDF]
    AAMAS-18. International Conference on Autonomous Agents and Multiagent Systems. 2018.

  • Bryan Wilder, Yevgeniy Vorobeychik.
    Controlling Elections through Social Influence. [arXiv] [PDF] [Supplement]
    AAMAS-18. International Conference on Autonomous Agents and Multiagent Systems. 2018.

  • Lily Hu, Bryan Wilder, Amulya Yadav, Eric Rice, and Milind Tambe.
    Activating the "Breakfast Club": Modeling Influence Spread in Natural-World Social Networks. [arXiv]
    AAMAS-18. International Conference on Autonomous Agents and Multiagent Systems. 2018.

  • Bryan Wilder, Sze-Chuan Suen, Milind Tambe.
    Preventing infectious disease in dynamic populations under uncertainty. [PDF] [Supplement]
    AAAI-18. AAAI Conference on Artificial Intelligence. 2018.

  • Bryan Wilder.
    Equilibrium computation and robust optimization in zero sum games with submodular structure. [arXiv] [Code]
    AAAI-18. AAAI Conference on Artificial Intelligence. 2018.

  • Bryan Wilder.
    Risk-sensitive submodular optimization. [PDF] [Supplement] [Code]
    AAAI-18. AAAI Conference on Artificial Intelligence. 2018.

  • Bryan Wilder, Nicole Immorlica, Eric Rice, Milind Tambe.
    Maximizing influence in an unknown social network. [PDF] [Supplement]
    AAAI-18. AAAI Conference on Artificial Intelligence. 2018.

  • Amulya Yadav, Bryan Wilder, Robin Petering, Eric Rice, Milind Tambe.
    Influence Maximization in the Field: The Arduous Journey from Emerging to Deployed Application. [PDF]
    AAMAS-17. International Conference on Autonomous Agents and Multiagent Systems. 2017.
    Nominated for Best Paper (7 out of 288 papers)

  • Bryan Wilder, Amulya Yadav, Nicole Immorlica, Eric Rice, Milind Tambe.
    Uncharted but not Uninfluenced: Influence Maximization with an Uncertain Network. [PDF] [Supplement]
    AAMAS-17. International Conference on Autonomous Agents and Multiagent Systems. 2017.

  • Shahrzad Gholami, Bryan Wilder, Matthew Brown, Dana Thomas, Nicole Sintov, Milind Tambe.
    Divide to Defend: Collusive Security Games.
    GameSec-16. Conference on Decision and Game Theory for Security. 2016.

  • Bryan Wilder and Gita Sukthankar.
    Sparsification of Social Networks Using Random Walks. [PDF] [Code]
    SocialCom-15. International Conference on Social Computation. 2015.
Journal Publications
  • Eric Rice, Robin Petering, Amanda Yoshioka-Maxwell, Jaih Craddock, Darlene Woo, Nicole Wilson, Laura Onasch-Vera, Bryan Wilder Amulya Yadav, Milind Tambe.
    Piloting the Use of Artificial Intelligence to Enhance HIV Prevention Interventions for Youth Experiencing Homelessness.
    Journal of the Society for Social Work and Research. Forthcoming.

  • Anne Kandler, Bryan Wilder, Laura Fortunato.
    Inferring individual-level processes from population-level patterns in cultural evolution. [Full text] [Code]
    Royal Society Open Science. 2017.

  • Bryan Wilder and Anne Kandler.
    Inference of Cultural Transmission Modes Based on Incomplete Information. [PDF]
    Human Biology. 2015.

  • Bryan Wilder and Kenneth O. Stanley.
    Reconciling Explanations for the Evolution of Evolvability. [PDF]
    Adaptive Behavior. 2015.

  • Bryan Wilder and Kenneth O. Stanley.
    Altruists Proliferate Even When at a Selective Disadvantage Within their Own Niche. [Full text]
    PLOS One. 2015.