Colin White

About

I design algorithms that create advanced AI algorithms.

I am Head of Research at Abacus.AI in San Francisco. Our work focuses on automating the search for high-performing deep learning models, as well as explaining and de-biasing them, from both a theoretical and empirical lens. Much of my work involves designing innovative methods by drawing insights from large-scale studies (ref1, ref2, ref3) and designing tools for better benchmarking of machine learning techniques (ref4, ref5, ref6).

I graduated from Carnegie Mellon University with a Ph.D. in computer science, advised by Nina Balcan and supported by the NDSEG Fellowship. I received my undergraduate degree from Amherst College.

For more, see my CV (last updated Sep. 2022).

News

    • • I am a Program Chair for AutoML-Conf 2023. Stay tuned for more information!
    • • Nov 2, 2022: I am giving a talk at UC Berkeley. My slides are here.
    • • Oct 11, 2022: I gave a talk at the AutoML Fall School 2022. My slides are here.
    • • Aug 17, 2022: I gave a talk at Microsoft Research. See the slides here.
    • • Jul 25, 2022: I gave a tutorial on neural architecture search with Debadeepta Dey, at AutoML-Conf 2022. View the talk here, and the slides here.
    • • Jul 19, 2021: we achieved second place in the Unseen Data in Neural Architecture Search competition at CVPR 2021 (certificate)!

Preprints

Publications

Professional
Service

  • Local Chair and Area Chair for AutoML-Conf 2022.
    Co-organizer for the 8th AutoML Workshop at ICML 2021.
    Top 10% of reviewers at NeurIPS 2022
    Top 10% of reviewers at ICML 2022
    Top 10% of reviewers at ICLR 2022
    Top 10% of reviewers at NeurIPS 2021
    Top 10% of reviewers at ICML 2021
    Top 10% of reviewers at NeurIPS 2020
    Top 50% of reviewers at NeurIPS 2019