Contact

Availability
Address Phone e-mail
Computer Science and Engineering, Room 6452 chrdimi
Chalmers university of technology +46 31772 1044 @
SE-41296 Göteborg chalmers.se

Currently teaching at the University of Lille (CRISTAL and INRIA-Sequel). Also visiting ETHZ; visiting faculty at Harvard. At Chalmers only once per month. Check out my availability

Research


Publications [By year] [By topic]

My research involves decision theory, reinforcement learning, statistical inferenceand optimisation, privacy and security

.

Software


Beliefbox - Statistical inference and decision making toolbox. Please cite using [BibTeX]

TORCS - The Open Racing Car Simulation [PDF] Please cite using [BibTeX]

News

  • Special issue on Decision Making for Network Security and Privacy. Deadline 31 July 2016
  • AAAI-2016

    Two new papers on differential privacy:

    1. Aristide Tossou and Christos Dimitrakakis. Algorithms for differentially private multi-armed bandits.
    2. Zuhe Zhang, Benjamin Rubinstein and Christos Dimitrakakis. On the differential privacy of Bayesian inference.
  • Lille

    Currently at INRIA and Univ-Lille-3. At Chalmers approximately once every two weeks.

  • VR Grant.

    Looking for a highly motivated PhD student to work on the project Learning, Privacy and the Limits of Computation (at Chalmers)

  • MoRE Vastra Gotaland / Marie Curie Grant with Harvard

    Christos Dimitrakakis (Chalmers) and David Parkes (Harvard), obtained a grant for the project Market Mechanisms for Multiple Minds. covering a year-long visit of Dimitrakakis to Harvard.

  • FLI Grant for two Phd students

    David Parkes (Harvard) and Christos Dimitrakakis (Chalmers, Lille), obtained a grant from the Future of Life Institute for the project Mechanism design for AI architectures. Looking for one PhD student, interested in Machine Learning and Game Theory (in Europe)

    AI-Sec 2015

    I am a co-organiser of the 8th ACM Workshop on Artificial Intelligence and Security: AI-Sec 2015

  • Reinforcement Learning Competition

    I am a co-organiser of the revived: Reinforcement learning competition - We are looking for new domain submissions, volunteers and prize donations. Please e-mail me if you are interested in helping out.

  • We are organising a Machine Learning Summer School April 14-16, 2015.
  • Our paper On selecting the nonce length in distance bounding protocols received the Computer Journal Wilkes Award for 2014.
  • September 17, 2014. Lecture on Sequential Decision Making: Experiment Design, Big Data and Reinforcement Learning at the machine learning seminar of Linkoping university.
  • Tutorial on Decision theory, experiment design and reinforcement learning at the MPI Autonomous Learning Summer School, September 1, 2014.
  • ICML 2014 Workshop on Learning, Security and Privacy

Teaching


I primarily cover topics in algorithms, decision making and estimation.

Student projects

PhD position filled

Secure and private machine learning and decision making.

Master student projects

The following projects are currently open, but I am willing to supervise any project related to artificial intelligence, decision theory and statistics. I can take on new students starting fall 2015.

Currently running projects

  • Approximate distributed learning and decision making.

Recently completed projects.

  • Adaptive experiment design for drug development.
  • Recommendation system evaluation.
  • Sampling scheemes for large-scale news recommendation.
  • Identity bridging.
  • Learning to play games from databases of suboptimal play.
  • Reinforcement learning in large discrete domains.
  • Learning to play games from multiple imperfect teachers.
  • Large-scale content extraction from heterogeneous sources.
  • Robust Optimisation and Minimax Bayesian reinforcement learning.