Ellen Vitercik

prof_pic.jpg

vitercik@stanford.edu

FAQ

I am an Assistant Professor at Stanford University, jointly appointed in the Management Science and Engineering and Computer Science departments.

My research spans machine learning, algorithm design, and discrete and combinatorial optimization, including the interface between economics and computation. I am especially interested in using machine learning for discrete optimization and algorithmic reasoning; see my course on the subject.

Before joining Stanford, I was a Miller fellow at UC Berkeley, hosted by Michael Jordan and Jennifer Chayes. I received a PhD in Computer Science from Carnegie Mellon University, where I was advised by Nina Balcan and Tuomas Sandholm.

My research has been recognized by a Schmidt Sciences AI2050 Early Career Fellowship and an NSF CAREER award. My thesis won the SIGecom Doctoral Dissertation Award, the CMU School of Computer Science Distinguished Dissertation Award, and the Honorable Mention Victor Lesser Distinguished Dissertation Award.

Miscellaneous information:

  • I pronounce my last name VIH-ter-sik.
  • People often ask me about my tiny phone, which I’ve used and loved for the past five years.
  • I grew up in the beautiful town of Lincoln, Vermont.

selected publications

  1. Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures
    Yu He, Yingxi Li, Colin White, and Ellen Vitercik
    In International Conference on Machine Learning (ICML), 2026
  2. Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty
    Wenshuo Guo, Nika Haghtalab, Kirthevasan Kandasamy, and Ellen Vitercik
    Operations Research, 2026
    Supersedes the EC’23 conference version.
  3. Algorithms with Calibrated Machine Learning Predictions
    Judy Hanwen Shen, Ellen Vitercik, and Anders Wikum
    In International Conference on Machine Learning (ICML), 2025
  4. How Much Data Is Sufficient to Learn High-performing Algorithms?
    Maria-Florina Balcan, Dan DeBlasio, Travis Dick, Carl Kingsford, Tuomas Sandholm, and Ellen Vitercik
    Journal of the ACM, 2024
    Supersedes the STOC’21 conference version.
  5. Learning to Branch: Generalization Guarantees and Limits of Data-Independent Discretization
    Maria-Florina Balcan, Travis Dick, Tuomas Sandholm, and Ellen Vitercik
    Journal of the ACM, 2024
    Supersedes the ICML’18 conference version.