My name is Behzad Tabibian, I am a PhD student at Max Planck Institute, Emperical inference department with Prof. Dr. Bernhard Schölkopf and Dr. Manuel Gomez Rodriguez. I studied Computer Science at Edinburgh University and graduated in June of 2012 and completed my masters at university of Pittsburgh. My main research interests are Machine Learning, Statistics and Inference. I primarily apply Machine Learning on (Social) Networks problems.

Previously I was interested in robotics and software engineering. In my free time I enjoy talking about books, particularly history, political philosophy and philosophy of science.

Recent News

Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation @ Prioritising Online Content Workshop - NIPS 2017

November 17, 2017

We will present our recent paper Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation at workshop on Prioritising Online Content at NIPS 2017, Long Beach CA, USA. The workshop is on Dec. 9th. We will present a long talk on this work in the morning between 10:30-11:50.

Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation @ WSDM 2018

October 22, 2017

Our paper, Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation, has been accepted (for a long talk) at 2018 ACM Web Search and Data Mining conference, Los Angles CA, USA. Project webpage and preprint of the paper are now available.

Optimizing Human Learning @ Teaching Machines, Robots, and Humans Workshop - NIPS 2017

October 20, 2017

Our paper, "Optimizing Human Learning", has been accepted at Teaching Machines, Robots, and Humans Workshop at NIPS 2017, Long Beach CA, USA. The workshop is on Dec. 9, further details about time and format of the presentation will be announced soon.

2017 MPI-ETH Center for Learning Systems retreat

October 04, 2017

I will be participating in 2017 MPI-ETH Center for Learning Systems retreat at Stoos, Switzerland. I will also give a talk on our latest work, "Optimizing Human Learning".

Design and Analysis of the NIPS 2016 Review Process

August 30, 2017

In this report, we analyze several aspects of the data collected during the review process, including an experiment investigating the efficacy of collecting ordinal rankings from reviewers (vs. usual scores aka cardinal rankings). Our goal is to check the soundness of the review process we implemented and, in going so, provide insights that may be useful in the design of the review process of subsequent conferences. We introduce a number of metrics that could be used for monitoring improvements when new ideas are introduced.

Therefore the seeker after the truth is not one who studies the writings of the ancients and, following his natural disposition, puts his trust on them, but rather the one who suspects his faith in them and questions what he gathers from them, the one who submits to argument and demonstration, and not to the sayings of a human being whose nature is fraught with all kinds of imperfection and deficiency.
Thus the duty of man who investigates the writings of scientists, if learning the truth is his goal, is to make himself an enemy of all that he reads, and, applying his mind to the core and margins of its content, attack it from every side.
He should also suspect himself as he performs his critical examination of it, so that he may avoid falling into either prejudice or leniency.
Ibn al Haytham 965-1040

Recent Posts

Hacking into Evolutionary Dynamics

August 10, 2017

This notebook contains some implementations of algorithms and ideas discussed in "Evolutionary Dynamics" by M. Novak. For better undrestanding of the code and equtions please consult first five chapters of the book.

Tutorial on Latent Dirichlet Allocation

July 01, 2017

I gave a tutorial on Latent Dirichlet Allocation as part of PhD tutorials at our department. Here you can find the contents I covered in this talk.