Aaron M. Ferber, PhD

data ⇄ decisions ⇆ deployment

AI for Science @ Cornell, Co-Organizer @ LXAI 

Previously USC CAIS / Meta AI / NEC Labs / Microsoft

prof_pic.png

Postdoc

Cornell University

Bowers CIS


Technical Instructor

CU AI for Science Institute

I’m Aaron Ferber, a researcher, engineer, and community builder bridging the gaps between AI, science, and society. I’m currently a postdoc at Cornell University working with Carla Gomes in the CU AI for Science Institute.

I’m passionate about solving impactful real-world problems with elegant and efficient solutions. My research experience focuses on end-to-end integration of deep learning and automated reasoning, with applications in several domains such as wildlife trafficking, invasive species management, neuroscience, photonic design, recommendation systems, finance, and more.

I received my PhD from the University of Southern California, advised by Prof. Bistra Dilkina, working in the Center for AI in Society (CAIS), with a disseration titled “Artificial Decision Intelligence: Integrating Deep Learning and Combinatorial Optimization”.

Outside of research I enjoy raquet sports, climbing, cooking, sailing, diving, and pretty much anything outdoors. I’m always looking for new things in research and recreation so reach out and let’s do something!

selected publications

  1. Submission
    Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization
    Utku Umur Acikalin, Aaron Ferber, and Carla P. Gomes
    Submission, 2024
  2. Submission
    AISciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification
    Brendan Hogan Rappazzo, Anmol Kabra, Felipe Siqueira Pacheco, Laura Greenstreet, Joshua Fan, Aaron Ferber, Marta Eichemberger Ummus, Alecsander Gomes Brito, Olivia J. Graham, Lillian R. Aoki, C. Drew Harvell, Alexander Flecker, and Carla P. Gomes
    Submission, 2024
  3. ICMLA
    GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation
    Brendan Hogan Rappazzo, Yingheng Wang, Aaron Ferber, and Carla Gomes
    ICMLA, 2024
  4. ICMLA
    Critic Loss for Image Classification
    Brendan Hogan Rappazzo, Aaron Ferber, and Carla Gomes
    ICMLA, 2024
  5. Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
    Lingkai Kong, Yuanqi Du, Wenhao Mu, Kirill Neklyudov, Valentin De Bortol, Haorui Wang, Dongxia Wu, Aaron Ferber, Yi-An Ma, Carla P Gomes, and Chao Zhang
    arXiv preprint arXiv:2402.18012, 2024
  6. GenCO: Generating Diverse Designs with Combinatorial Constraints
    Aaron Ferber, Arman Zharmagambetov, Taoan Huang, Bistra Dilkina, and Yuandong Tian
    In Forty-first International Conference on Machine Learning, 2024
  7. Contrastive Predict-and-Search for Mixed Integer Linear Programs
    Taoan Huang, Aaron Ferber, Arman Zharmagambetov, Yuandong Tian, and Bistra Dilkina
    In Forty-first International Conference on Machine Learning, 2024
  8. Landscape surrogate: Learning decision losses for mathematical optimization under partial information
    Arman Zharmagambetov, Brandon Amos, Aaron Ferber, Taoan Huang, Bistra Dilkina, and Yuandong Tian
    In Advances in Neural Information Processing Systems, 2024
  9. arxiv
    Distributional MIPLIB: a Multi-Domain Library for Advancing ML-Guided MILP Methods
    Weimin Huang, Taoan Huang, Aaron Ferber, and Bistra Dilkina
    arXiv preprint arXiv:2406.06954, 2024
  10. Interdiction of wildlife trafficking supply chains: An analytical approach
    Emily C Griffin, Aaron Ferber, Lucas Lafferty, Burcu B Keskin, Bistra Dilkina, and Meredith Gore
    IISE Transactions, 2024
  11. Surco: Learning linear surrogates for combinatorial nonlinear optimization problems
    Aaron Ferber, Taoan Huang, Daochen Zha, Martin Schubert, Benoit Steiner, Bistra Dilkina, and Yuandong Tian
    In International Conference on Machine Learning, 2023
    \textcolorred\textbfBest Paper ICML 2024 SODS Workshop
  12. Predicting Wildlife Trafficking Routes with Differentiable Shortest Paths
    Aaron Ferber, Emily Griffin, Bistra Dilkina, Burcu Keskin, and Meredith Gore
    In International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 2023
  13. Local branching relaxation heuristics for integer linear programs
    Taoan Huang, Aaron Ferber, Yuandong Tian, Bistra Dilkina, and Benoit Steiner
    In International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 2023
  14. Searching large neighborhoods for integer linear programs with contrastive learning
    Taoan Huang, Aaron Ferber, Yuandong Tian, Bistra Dilkina, and Benoit Steiner
    In International Conference on Machine Learning, 2023
  15. Advancing interdisciplinary science for disrupting wildlife trafficking networks
    Meredith L Gore, Emily Griffin, Bistra Dilkina, Aaron Ferber, Stanley E Griffis, Burcu B Keskin, and John Macdonald
    Proceedings of the National Academy of Sciences, 2023
  16. A data directory to facilitate investigations on worldwide wildlife trafficking
    Meredith L Gore, Rowan Hilend, Jonathan O Prell, Emily Griffin, John R Macdonald, Burcu B Keskin, Aaron Ferber, and Bistra Dilkina
    Big Earth Data, 2023
  17. Quantitative investigation of wildlife trafficking supply chains: A review
    Burcu B Keskin, Emily C Griffin, Jonathan O Prell, Bistra Dilkina, Aaron Ferber, John MacDonald, Rowan Hilend, Stanley Griffis, and Meredith L Gore
    Omega, 2023
  18. Identifying datasets for global wildlife trafficking
    Meredith Gore, Burcu Keskin, John Macdonald, Aaron Ferber, Emily Griffin, Oakley Prell, Bistra Dilkina, and Rowan Hilend
    2022
  19. CP
    Learning Lagrangian Multipliers for the Travelling Salesman Problem
    Augustin Parjadis, Quentin Cappart, Bistra Dilkina, Aaron Ferber, and Louis-Martin Rousseau
    In Principles and Practice of Constraint Programming, 2024
    \textcolorred\textbfBest Paper CP 2024
  20. Erratum to “budgeted prize-collecting traveling salesman and minimum spanning tree problems”
    Alice Paul, Daniel Freund, Aaron Ferber, David B Shmoys, and David P Williamson
    Mathematics of Operations Research, 2023
  21. Learning pseudo-backdoors for mixed integer programs
    Aaron Ferber, Jialin Song, Bistra Dilkina, and Yisong Yue
    In International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research, 2022
  22. Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation
    Umang Gupta, Aaron Ferber, Bistra Dilkina, and Greg Ver Steeg
    Proceedings of the AAAI Conference on Artificial Intelligence, May 2021
  23. Mipaal: Mixed integer program as a layer
    Aaron Ferber, Bryan Wilder, Bistra Dilkina, and Milind Tambe
    In Proceedings of the AAAI Conference on Artificial Intelligence, May 2020
  24. OR
    Budgeted prize-collecting traveling salesman and minimum spanning tree problems
    Alice Paul, Daniel Freund, Aaron Ferber, David B Shmoys, and David P Williamson
    Mathematics of Operations Research, May 2020
  25. ESA
    Prize-collecting TSP with a budget constraint
    Alice Paul, Daniel Freund, Aaron Ferber, David B Shmoys, and David P Williamson
    In European Symposium on Algorithms, May 2017