Interpretable Comparison of Generative Models

Wittawat Jitkrittum - Research Scientist at Google Research
Data Science

Date: November 5th 2020
Location: Eurecom - Eurecom

Abstract: Given two generative models (e.g., two GAN models), and a set of target observations (e.g., real images), how do we know which model is better? In this talk, I will introduce recently developed kernel-based distance measures that will help us answer this question. These measures can be used to construct a nonparametric, computationally efficient statistical test to systematically measure the relative goodness of fit of the two candidate models. As a unique advantage, the test can produce a set of examples showing where one model fits significantly better than the other. No deep background knowledge on kernel methods or statistical testing is needed for this talk. All prerequisites will be introduced. Bio: Wittawat Jitkrittum is a research scientist at Google Research. From 2018 to 2020, he was a postdoctoral researcher working with Bernhard Schoelkopf at Max Planck Institute for Intelligent Systems, Tuebingen, Germany. He earned his PhD in 2017 from Gatsby Unit, University College London with a thesis on informative features for comparing distributions. He received a best paper award at NeurIPS 2017 and the ELLIS PhD award 2019 for outstanding dissertation. Wittawat has broad research interests covering kernel methods, large-scale supervised learning, and approximate Bayesian inference. He serves as a workflow chair for AISTATS 2021, a publication chair for AISTATS 2016, and is a co-organizer of the Machine Learning Summer School 2020.


Permalink: https://www.eurecom/seminar/98286