Nico Christianson

I am an incoming Assistant Professor in the Department of Computer Science at Johns Hopkins University (starting in Fall 2026); I will be affiliated with the Data Science and AI Institute and the Ralph O’Connor Sustainable Energy Institute.
📢 I am recruiting PhD students and postdocs to join my group at Johns Hopkins in Fall 2026. Learn more →

My research lies broadly at the intersection of algorithms, machine learning, and optimization. I am particularly interested in developing theoretically-grounded algorithms and AI/ML frameworks for reliable decision-making under uncertainty, motivated by applications of broad societal importance like energy and computing systems. My recent interests include:

  • online and learning-augmented algorithms
  • uncertainty quantification for risk-aware decision-making
  • machine learning for optimization
  • applications to energy resource optimization and data center workload scheduling

Before joining Johns Hopkins, I will be spending a year as a Stanford Energy Postdoctoral Fellow, hosted by Ellen Vitercik and Ram Rajagopal. Previously, I did my PhD in Computing and Mathematical Sciences at Caltech, where I had the good fortune of working with Adam Wierman and Steven Low. My PhD was supported in part by an NSF Graduate Research Fellowship and a PIMCO Data Science Fellowship, and my dissertation won the Ben P.C. Chou Doctoral Prize in Information Science and Technology and the Demetriades-Tsafka-Kokkalis Prize in Renewable Energy. Before Caltech, I was an undergrad in applied math at Harvard.

selected publications (full list →)

  1. Optimal Robustness-Consistency Tradeoffs for Learning-Augmented Metrical Task Systems
    Nicolas Christianson, Junxuan Shen, and Adam Wierman
    International Conference on Artificial Intelligence and Statistics, 2023
  2. Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
    Christopher Yeh, Nicolas Christianson, Adam Wierman, and 1 more author
    Neural Information Processing Systems, 2025
  3. Fast and Reliable N−k Contingency Screening with Input-Convex Neural Networks
    Nicolas Christianson, Wenqi Cui, Steven Low, and 2 more authors
    Learning for Dynamics & Control Conference, 2025
  4. Learning-Augmented Competitive Algorithms for Spatiotemporal Online Allocation with Deadline Constraints
    Adam Lechowicz, Nicolas Christianson, Bo Sun, and 4 more authors
    ACM SIGMETRICS, 2025
  5. Online Algorithms with Uncertainty-Quantified Predictions
    Bo Sun, Jerry Huang, Nicolas Christianson, and 3 more authors
    International Conference on Machine Learning, 2024

upcoming talks

Feb 17, 2026 RAIN Seminar at Stanford

recent news (older →)

Dec 12, 2025 Two papers accepted to ACM SIGMETRICS 2026: one on online smoothed demand management and another on prediction-specific design of learning-augmented algorithms. Many thanks to my wonderful collaborators!
Dec 02, 2025 I am at NeurIPS in San Diego this week! Our paper on End-to-End Conformal Risk Control will be presented in the poster session on Wednesday.
Nov 05, 2025 I gave a talk on risk-sensitive online algorithms in the CS Theory Seminar at UMass Amherst. Thanks to my wonderful collaborators Adam Lechowicz and Mohammad Hajiesmaili for hosting me!
Oct 27, 2025 It was great attending INFORMS in Atlanta and and catching up with so many collaborators and friends! I gave a talk on end-to-end learning for contingency screening in the session “Human-Centric Energy Markets.”
Oct 22, 2025 Our paper End-to-End Conformal Calibration for Optimization Under Uncertainty was accepted at Transactions on Machine Learning Research