Noah Golowich
I am a postdoctoral researcher at Microsoft Research, NYC. In 2026, I will join the computer science department at UT Austin as an Assistant Professor. I completed my PhD at MIT, where I was very fortunate to be advised by Constantinos Daskalakis and Ankur Moitra.
My research focuses on obtaining provable guarantees to aid our understanding of machine learning algorithms in settings beyond the scope of classical frameworks, such as those involving multiple agents or a dynamic environment. My work includes both upper and lower bounds for the convergence of multi-agent learning algorithms, as well as algorithms with computational and statistical guarantees for learning near-optimal policies in the setting of reinforcement learning. My research interests additionally span learning theory more broadly, including differential privacy and combinatorial problems in learning theory.
My research focuses on obtaining provable guarantees to aid our understanding of machine learning algorithms in settings beyond the scope of classical frameworks, such as those involving multiple agents or a dynamic environment. My work includes both upper and lower bounds for the convergence of multi-agent learning algorithms, as well as algorithms with computational and statistical guarantees for learning near-optimal policies in the setting of reinforcement learning. My research interests additionally span learning theory more broadly, including differential privacy and combinatorial problems in learning theory.
Contact information:
n$g at mit dot edu, replace the $ with z
CSAIL
MIT EECS
32 Vassar Street
Cambridge, MA 02139
