I am a postdoctoral researcher at Empirical Inference Department, Max Planck Institute for Intelligent Systems working with Bernhard Schölkopf. I work in the field of machine learning (intersection of computer science and statistics). My research topics include (but not limited to)

  • Fast (linear runtime) non-parametric statistical tests
  • Kernel-based representation of data
  • Deep generative modelling of images
  • Approximate Bayesian inference
I completed my PhD study at Gatsby Unit, UCL where I worked with Arthur Gretton on various topics related to kernel methods and Bayesian inference. My CV is here.


  • Please feel free to contact me for a research discussion.
  • If you are a student working in a field related to machine learning, and are looking for an internship opportunity (for 2-6 months) at the Empirical Inference department, please contact me.

Contact: Wittawat Jitkrittum (วิทวัส จิตกฤตธรรม) ( )

Wittawat Jitkrittum
Max Planck Institute for Intelligent Systems
Max-Planck-Ring 4
72076 Tuebingen
Phone: +49 7071 601


22 Apr 2019

Our paper titled “Kernel Mean Matching for Content Addressability of GANs” has been accepted to ICML 2019. This work proposes a procedure which adds “content addressability” to any pre-trained implicit model (including GANs). Given a set of input images, the procedure can generate images (from the chosen implicit model) that are similar to the input images, without retraining the model.

21 Mar 2019

I am a co-organizer of the first Southeast Asia Machine Learning (SEA ML) School to be held in Jakarta, Indonesia on 8-12 July 2019. Application is now open. Deadline: 20 April 2019. No registration fee for students.

29 Jan 2019

New preprint: Witnessing Adversarial Training in Reproducing Kernel Hilbert Spaces. In this work, we augment GAN’s loss function with a new term that provides more information about what the generator learns during training.

20 Dec 2018

I spoke at the Symposium on frontier research in information science and technology at VISTEC, Thailand. Topic: Recent Advances in Kernel Methods for Model Criticism. Slides.

3 Nov 2018

We have released Python code for “Informative Features for Model Comparison”.

30 Oct 2018

New preprint: Large sample analysis of the median heuristic. In this work, we theoretically study the commonly used median heuristic for setting the bandwidth of a Gaussian kernel.

30 Oct 2018

Our NIPS paper “Informative Features for Model Comparison” is now online on Arxiv. Python code.

7 Sep 2018

Our paper titled “Informative Features for Model Comparison” was accepted to NIPS 2018. Given two samples from two candidate models, and a reference sample (observed data), the goal is to design a statistical test to determine which of the two samples is closer to the reference sample. This has an application for comparing two GAN models.

21 Mar 2018

I was invited to speak at Department of Mathematics and Computer Science, Chulalongkorn University. Topic: A Technical Introduction to Kernel Goodness-of-Fit Testing.

16 Mar 2018

I was invited to speak at VISTEC, Wangchan Valley, Rayong, Thailand. Topic: Machine Learning Fundamentals. Event details. Slides.

7 Mar 2018

I was invited to give a talk at the BKK Machine Learning Meetup event. Topic: Introduction to kernel methods for comparing distributions. Slides.

20 Feb 2018

I was invited to give a talk at the Workshop on Functional Inference and Machine Intelligence (19-21 Feb 2018), Tokyo. Slides.

24 Jan 2018

The podcast we did with This Week in Machine Learning & AI on our NIPS Best Paper 2017 was published here.

1 Jan 2018

I started working remotely as a postdoc at Max Planck Institute for Intelligent Systems with Bernhard Schölkopf.

18 Dec 2017

I gave a 50-minute presentation on A Linear-Time Kernel Goodness-of-Fit Test (NIPS 2017 best paper). Download slides.

5 Dec 2017

I gave an oral presentation at NIPS 2017 on A Linear-Time Kernel Goodness-of-Fit Test. The paper was selected for one of three best paper awards at NIPS 2017. Python code here. Presentation slides here. Talk video here.

4 Sep 2017

Our paper A Linear-Time Kernel Goodness-of-Fit Test has been accepted for oral presentation at NIPS 2017. Python code.

1 Aug 2017

I gave an oral presentation at ICML 2017 on our new linear-time independence test. The slides are here.

1 Jul 2017

Uploaded slides for the linear-time nonparametric goodness-of-fit test.

1 Jun 2017

We have released Python code for our linear-time nonparametric goodness-of-fit test.

Last update: 22-Apr-19
Based on al-folio theme.