PhD position in in Mathematical Machine Learning

Functieomschrijving

The Korteweg-de Vries Institute for Mathematics (KdVI) of the University of Amsterdam invites you to apply for a PhD position in mathematical machine learning. We are looking for a highly motivated and enthusiastic researcher (F/M), who likes to work in an internationally oriented environment;

You will be working under supervision of Dr Tim van Erven to design and mathematically analyze new machine learning algorithms. The ambition is to publish at top-level international conferences and journals, like COLT, NeurIPS, the Journal of Machine Learning Research, etc. Possible topics include:

Adaptive Online Learning: Online learning deals with learning algorithms that process data sets sequentially, one data point at a time. Such algorithms play a key role in machine learning for very large data sets, for instance when training deep neural networks. The goal of this project is to develop new online learning algorithms and prove that they are optimal for multiple types of loss functions and under multiple different types of assumptions, without the need to manually tune any hyperparameters.

Mathematical Formalization and Analysis of Explainability Methods: Recently there has been much interest in generating explanations that clarify and communicate how machine learning methods make their decisions. But none of the existing methods gives any formal mathematical guarantees on how well they can be expected to work and under which conditions their explanations can be trusted. The goal of this project is to formalize explainability and to design new methods with provable guarantees.

What are you going to do?

You will:

• perform research on mathematical machine learning;
• be part of the research programme Stochastics and interact with its senior and junior members;
• contribute to educational programmes at the University of Amsterdam.

Functie-eisen