About me 

I am a  third year PhD student at the University of Wisconsin-Madison, advised by Prof. Dimitris Papailiopoulos . My research interests involve Large Language Models, general 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. How Well Can Transformers Emulate In-context Newton's Method?
   Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris Papailiopoulos and Jason Lee.
   Arxiv Link

2. Looped Transformers as Programmable Computers
   Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason Lee, Dimitris Papailiopoulos (ICML 2023).
   Arxiv link 

3. The Expressive Power of Tuning Only the Normalization Layers

Angeliki Giannou, Shashank Rajput, Dimireis Papailiopoulos (COLT 2023).
Arxiv link 

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

5. 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).

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

For an updated list of publications, please visit my Google Scholar

Service

Reviewer: NeurIPS 21-23, ICML 2023-2024, ICLR 2024-2025, ALT 2024-2025, COLM 2024
Outstanding Reviewer Award:  NeurIPS 2021, 2022 (top 8%)
Organizer of MLOpt-Idea Seminar
Organizer of FITML Workshop @ NeurIPS