Emmanouil (Manolis) Zampetakis

Welcome! I am a PhD student in the Department of Electrical Engineering and Computer Science of Massachusetts Institute of Technology (MIT) . I am very fortunate to be advised by Constantinos Daskalakis.

My research interest include: Theoretical Machine Learning, Learning Theory, Sublinear Algorithms and Algorithmic Game Theory.

Email: mzampet [at) mit(dot]edu
CV: pdf

About

I joined the graduate program of MIT on September 2014 in the Theory of Computation Group at CSAIL . My research advisor is Constantinos Daskalakis and we are working on a wide range of problems on theoretical machine learning, learning theory, complexity theory and algorithmic game theory.

Before MIT, I was an undergrad student at the Department of Electrical Engineering and Computer Science at National Technical University of Athens where I completed my Diploma Degree. During my time there, I was fortunate to work with Dimitris Fotakis on Mechanism Design with Verification and Scheduling Map-Reduce jobs.

During the Summer 2017 I joined as an intern the Algorithms and Optimization Group at Google Research at New York where I worked with Alessandro Epasto , Mohammad Mahdian and Vahab Mirrokni on Differential Privacy with applications to Mechanism Design.

Starting at Fall 2018 my research will be supported by Google PhD Fellowship.

Research Papers

  1. Learning from Unreliable Datasets
    31th Conference on Learning Theory COLT 2018
  2. A Converse to Banach's Fixed Point Theorem and its CLS Completeness
    50th Annual ACM Symposium on the Theory of Computing STOC 2018
  3. Bootstrapping EM via Power EM and Convergence in the Naive Bayes Model
    21st International Conference on Artificial Intelligence and Statistics AISTATS 2018
  4. Ten Steps of EM Suffice for Mixtures of Two Gaussians
    30th Conference on Learning Theory COLT 2017
  5. Faster Sublinear Algorithms using Conditional Sampling
    28th ACM-SIAM Symposium on Discrete Algorithms SODA 2017
  6. Mechanism Design with Selective Verification
    17th ACM Economics and Computation EC 2016
  7. Efficient Money Burning in General Domains
    8th International Symposium on Algorithmic Game Theory SAGT 2015 Special Issue for SAGT 2015
  8. Scheduling MapReduce Jobs and Data Shuffle on Unrelated Processors
    14th International Symposium on Experimental Algorithms SEA 2015
    Preliminary version: EDBT/ICDT Workshop on Algorithms for Map Reduce and Beyond, 2014.
  9. Truthfulness Flooded Domains and the Power of Verification for Mechanism Design
    9th Conference on Web and Internet Economics WINE 2013 Special Issue for WINE 2013