I am a fourth-year PhD student at Harvard, advised by Yaron Singer. I am part of the EconCS and the Harvard Machine Learning Theory groups.

My interests include Machine Learning, Algorithms and Optimization. Recently, I became interested in questions around neural networks. Specifically, why do our modern over-parametrized models generalize and what kind of theory do we need to develop to explain this phenomenon? Why are they susceptible to adversarial perturbations and how can we design more robust and interpretable models? For details please take a look at my publications.

Before coming to Harvard, I received my Bachelor's from the University of Athens where I was advised by Dimitris Fotakis. I worked in Algorithmic Game Theory and Selfish Routing.

I spent the summer of 2019 in the Core Data Science team at Facebook working with Henry C. Lin and Udi Weinsberg. During the summer of 2018 I interned in Microsoft Research in Beijing (MSRA) hosted by Wei Chen.

My CV can be found here (last updated: June 2019).

Email: kalimeris [at] g [dot] harvard [dot] edu


Robustness from Simple Classifiers (working paper)

with Sharon Qian, Gal Kaplun and Yaron Singer

SGD on Neural Networks Learns Functions of Increasing Complexity

with Preetum Nakkiran, Gal Kaplun, Tristan Yang, Benjamin L. Edelman, Fred Zhang and Boaz Barak

Annual Conference on Neural Information Processing Systems (NeurIPS) 2019

(spotlight presentation)

Preliminary version appeared in the 1st Workshop on Understanding and Improving Generalization in Deep Learning, ICML 2019

Robust Neural Networks are More Interpretable for Genomics

with Peter K. Koo, Sharon Qian, Gal Kaplun and Verena Volf

Preliminary version appeared in the ICML 2019 Workshop on Computational Biology

Robust Influence Maximization for Hyperparametric Models

with Gal Kaplun and Yaron Singer

International Conference of Machine Learning (ICML) 2019

Learning Diffusion using Hyperparameters

with Yaron Singer, Karthik Subbian and Udi Weinsberg

International Conference of Machine Learning (ICML) 2018

Improving Selfish Routing for Risk-Averse Players

with Dimitris Fotakis and Thanasis Lianeas

Web and Internet Economics (WINE) 2015


ICML 2020

Professional Experience

  • Summer 2019: Facebook Internship in Core Data Science group hosted by Henry C. Lin and Udi Weinsberg.
  • Summer 2018: MSR Asia Internship hosted by Wei Chen.
  • Summer 2014: Software Engineering internship at CERN, through CERN's summer student program.

Teaching Experience

Spring '19: AM 221: Advanced Optimization

Institution: Harvard

Instructor: Yaron Singer

Fall '17: CS 134: Networks (teaching excellence award)

Institution: Harvard

Instructor: Yaron Singer

Spring '16: Algorithmic game Theory

Institution: DIT

Instructor: Dimitris Fotakis

Fall '16: Mathematics for Computer Science, Theory of Computation

Institution: DIT

Instructor: Stavros Kolliopoulos