Angeliki Giannou

PhD student
University of Wisconsin, Madison
Email: giannou@wisc.edu

About me

I am a first year PhD student at the University of Wisconsin-Madison, advised by Prof. Dimitris Papailiopoulos . My research interests involve Machine Learning Theory, Learning Theory and Optimization.

Prior to that, I received a Bachelor & M. Sc. in Electrical and Computer Engineering from National and Technical University of Athens, working with Prof. Panayotis Mertikopoulos.

Publications

  1. Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information
    Angeliki Giannou, Emmanouil Vlatakis, Panayotis Mertikopoulos (COLT 2021).
    Arxiv link

  2. On the Rate of Convergence of Regularized Learning in Games: From Bandits and Uncertainty to Optimism and Beyond
    Angeliki Giannou, Emmanouil Vlatakis, Panayotis Mertikopoulos (NeurIPS 2021).

  3. On the convergence of policy gradient methods to Nash equilibria in general stochastic games
    Angeliki Giannou, Kyriakos Lotidis, Emmanouil Vlatakis, Panayotis Mertikopoulos (NeurIPS 2022).

  4. The expressive power of tuning the normalization layers.
    Angeliki Giannou, Shashank Rajput, Dimitris Papailiopoulos (Preprint).



Awards

Outstanding Reviewer Award: NeurIPS 2021, NeurIPS 2022 (top 8%)

Presentations

The stability of no-regret learning : Link to presentation (in Greek) Seminar Corelab (2020)
Survival of the strictest: Stable and unstable equilibria under regularized learning. MLOpt Idea Seminar (2021)