Themis Gouleakis

I am a postdoctoral fellow at the Algorithms & complexity department of Max-Planck-Institute for informatics.

About

Previously, I have worked as a postdoctoral researcher at the University of Southern California supervised by Ilias Diakonikolas.

I completed my Ph.D. at MIT in 2018, affiliated with the Theory of Computation group in CSAIL and advised by Ronitt Rubinfeld.

I did my undergraduate studies at the National Technical University of Athens (Sept. 2005 - June 2011).

Journal Publications

• Sampling Correctors
  Clement L. Canonne, Themis Gouleakis, and Ronitt Rubinfeld
  SIAM Journal on Computing (SICOMP), 2018

• Testing shape restrictions of discrete distributions
  Clement L. Canonne, Ilias Diakonikolas,Themis Gouleakis, and Ronitt Rubinfeld.
  Theory of Computing Systems, 2017.
  Invited issue for STACS 2016.

• Sublinear-Time Algorithms for Counting Star Subgraphs via Edge Sampling
  Maryam Aliakbarpour, Amartya Shankha Biswas, Themis Gouleakis, John Peebles, Ronitt Rubinfeld, Anak Yodpinyanee.
  Algorithmica, 2017

• Collision-based Testers are Optimal for Uniformity and Closeness
  Ilias Diakonikolas, Themis Gouleakis, John Peebles, Eric Price
  Chicago Journal of Theoretical Computer Science (CJTCS), 2019

Conference Proceedings

• Optimal Testing of Discrete Distributions with High Probability.
  Ilias Diakonikolas, Themis Gouleakis,Daniel Kane, John Peebles, and Eric Price
  53rd Annual ACM Symposium on Theory of Computing (STOC), 2021 (to appear)

• Robust Learning under Strong Noise via SQs.
  Ioannis Anagnostides, Themis Gouleakis, and Ali Marashian
  24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021 (to appear)

• Secretary and Online Matching Problems with Machine Learned Advice.
  Antonios Antoniadis, Themis Gouleakis, Pieter Kleer, and Pavel Kolev
  34th Conference on Neural Information Processing Systems (NeurIPS), 2020

• Simple Local Computation Algorithms for the Lovász Local Lemma.
  Dimitris Achlioptas, Themis Gouleakis, and Fotis Iliopoulos
  32nd ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) 2020

• Distribution-Independent PAC Learning of Halfspaces with Massart Noise
  Ilias Diakonikolas, Themis Gouleakis, and Christos Tzamos
  33rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2019
  Selected for oral presentation

• Towards Testing Monotonicity of Distributions Over General Posets
  Maryam Aliakbarpour, Themis Gouleakis, John Peebles, Ronitt Rubinfeld, Anak Yodpinyanee.
  32nd Annual Conference on Learning Theory, (COLT) 2019

• Communication and Memory Efficient Testing of Discrete Distributions
  Ilias Diakonikolas,Themis Gouleakis, Daniel Kane, and Sankeerth Rao.
  32nd Annual Conference on Learning Theory, (COLT) 2019

• Computationally and Statistically Efficient Truncated Regression
  Costis Daskalakis, Themis Gouleakis, Christos Tzamos and Manolis Zampetakis
  32nd Annual Conference on Learning Theory, (COLT) 2019

• Efficient Statistics, in High Dimensions, from Truncated Samples.
  Costis Daskalakis, Themis Gouleakis, Christos Tzamos and Manolis Zampetakis
  59th Annual IEEE Symposium on Foundations of Computer Science, (FOCS) 2018

• Improved Massively Parallel Computation Algorithms for MIS, Matching, and Vertex Cover.
  Mohsen Ghaffari,Themis Gouleakis, Christian Konrad , Slobodan Mitrovic and Ronitt Rubinfeld
  ACM Symposium on Principles of Distributed Computing (PODC), 2018.

• Certified Computation from Unreliable Datasets
  Themis Gouleakis, Christos Tzamos and Manolis Zampetakis
  31st Annual Conference on Learning Theory, (COLT) 2018

• Sample-Optimal Identity Testing with High Probability
  Ilias Diakonikolas, Themis Gouleakis, John Peebles, and Eric Price
  45th International Colloquium on Automata, Languages and Programming (ICALP), 2018

• Faster Sublinear Algorithms using Conditional Sampling
  Themis Gouleakis, Christos Tzamos and Manolis Zampetakis
  28th ACM-SIAM Symposium on Discrete Algorithms (SODA), 2017.

• Testing shape restrictions of discrete distributions
  Clement L. Canonne, Ilias Diakonikolas,Themis Gouleakis, and Ronitt Rubinfeld.
  International Symposium on Theoretical Aspects of Computer Science (STACS), 2016

• Sampling Correctors
  Clement L. Canonne, Themis Gouleakis, and Ronitt Rubinfeld
  Innovations in Theoretical Computer Science (ITCS), 2016

• Algorithmic Improvements of the Lovasz Local Lemma via Cluster Expansion
  Dimitris Achlioptas, and Themis Gouleakis
  Foundations of Software Technology and Theoretical Computer Science (FSTTCS), 2012

Teaching

• Property testing.
  Max Planck Institute for Informatics, Winter 2020/2021

• Geometric algorithms with limited resources.
  Max Planck Institute for Informatics, Summer 2021

Awards and Honors

• Out­stand­ing Pa­per Award: 33rd An­nual Con­fer­ence on Neural In­for­ma­tion Pro­cess­ing Sys­tems, 2019
• Onassis Foundation Scholarship (2012-2015): Scholarship for doctoral studies.
• Paris Kanellakis Fellowship (2012-2013): Fellowship for first year MIT EECS students.