Noah Golowich

I am a 2nd year PhD student at MIT, working on theoretical machine learning. I am very fortunate to be advised by Constantinos Daskalakis.

I am grateful to be supported by a Hertz Foundation Fellowship and an NSF Graduate Fellowship. I was additionally supported by an MIT Akamai Fellowship in the academic year 2019-2020.

Contact information:
n$g at mit dot edu, replace the $ with z
CSAIL
MIT EECS
32 Vassar Street
Cambridge, MA 02139

Papers

Authors are in alphabetical order, unless indicated with ().
Preprints
  • Tight last-iterate convergence rates for no-regret learning in multi-player games.
    () Noah Golowich, Sarath Pattathil, and Constantinos Daskalakis.
    To appear at NeurIPS 2020.
  • Decoupled Policy Gradient Methods for Competitive Reinforcement Learning.
    Constantinos Daskalakis, Dylan Foster, and Noah Golowich.
    To appear at NeurIPS 2020.
  • Near-tight closure bounds for Littlestone and threshold dimensions.
    Badih Ghazi, Noah Golowich, Ravi Kumar, and Pasin Manurangsi.
  • On the power of multiple anonymous messages.
    Badih Ghazi, Noah Golowich, Ravi Kumar, Rasmus Pagh, and Ameya Velingker.
    Extended abstract at FORC 2020. [conf] [talk video] [slides]
    My presentation at MIT CIS seminar, December 2019. [slides]
Publications
Site design from Vasilios Mavroudis : Plain Academic