Willie Neiswanger

Machine learning at Stanford Computer Science SAIL / StatsML

I am a postdoc in computer science at Stanford University, working with Stefano Ermon and affiliated with the StatsML Group, Stanford AI Lab, and SLAC.

Research: I work on algorithms and systems to help scale and automate machine learning. My interests include distributed inference, AutoML, computer vision, computational biology, materials science, and analysis of text and network data. I also work on sequential decision making under uncertainty, which I apply to problems in science and engineering.

Education: I completed my PhD in Machine Learning at Carnegie Mellon University, where I was advised by Eric Xing and collaborated with Jeff Schneider and Barnabas Poczos.

Previously, I studied at Columbia University, where I worked with the Wiggins Lab and Frank Wood.


  • Jan 28, 2022 New paper on experimental design and model-based reinforcement learning in ICLR 2022.
  • Jan 1, 2022 New paper (+ website) on IS-Count, for large-scale object counting in images, in AAAI 2022.
  • Oct 15, 2021 Three papers (on uncertainty, explainability, and benchmarking in ML) in NeurIPS 2021.
  • July 14, 2021 Our paper on Pollux was awarded the Jay Lepreau Best Paper Award at OSDI'21.
  • June 10, 2021 New paper (+ website) on Bayesian Algorithm Execution (BAX) and InfoBAX, in ICML 2021.
  • June 1, 2021 I co-organized the Machine Learning for Data Workshop at ICML 2021.
  • Apr 1, 2021 New paper on Pollux, a deep learning cluster scheduler/tuner, in OSDI 2021 (+ AdaptDL).
  • Mar 16, 2021 New paper on uncertainty quantification with martingales for GPs in ALT 2021 (+ code).
  • Mar 9, 2021 New paper on active classification for catalyst discovery in the Journal of Chemical Physics.
  • Jan 12, 2021 New paper on interactive weak supervision in ICLR 2021 (+ code).
  • Dec 22, 2020 Released Uncertainty Toolbox, for predictive UQ, calibration, metrics, and visualization.
  • Dec 2, 2020 New paper on BANANAS for neural architecture search in AAAI 2021 (+ code).
  • Sep 25, 2020 New paper on encodings for neural architecture search in NeurIPS 2020 (spotlight).
  • July 10, 2020 New paper on understanding the prevalence of SARS-CoV-2 on medRxiv (+ MLD blog).
  • June 1, 2020 I co-organized the Real World Experiment Design and Active Learning Workshop at ICML 2020.
  • Mar 6, 2020 New paper on uncertainty quantification for materials property predictions in MLST.
  • Mar 5, 2020 New paper on Dragonfly, a system for scalable and robust Bayesian optimization in JMLR.
  • Jan 7, 2020 New paper on molecular optimization and synthesis route design in AISTATS 2020.
  • Dec 13, 2019 I co-organized the Learning with Rich Experience (LIRE) Workshop at NeurIPS 2019.
  • Sep 3, 2019 New paper on contextual optimization for nuclear fusion applications in NeurIPS 2019.
  • Aug 15, 2019 I defended my PhD thesis and graduated 🎉.
  • Aug 1, 2019 New paper on T cell synapse propensity in the Journal of Immunology.
  • Apr 21, 2019 New paper on experimental design, optimization, active learning, hybrid tasks, in ICML 2019.



A full list of my publications can be found here.