Skip to content
Main menu hidden.

Trade-offs in Nonconvex Learning

Research project WASP funded project in statistical learning, particularly in non-convex inference and learning.

WASP has a special program for developing the mathematics of AI and strengthen Sweden's position in the field. This project is a part of the WASP recruitment program and is intended to further develop the research environment within statistical learning, particularly in non-convex inference and learning, at the Department of Mathematics and Mathematical Statistics, Umeå University. The project contains a large recruitment package including one tenure track assistant professorship, one PhD student, two postdocs, and discretionary funds, with a budget about 14 MSEK in 5 years.

Head of project

Jun Yu

Project overview

Project period:

2022-04-01 2027-03-31

Participating departments and units at Umeå University

Department of Mathematics and Mathematical Statistics

Research area

Mathematics, Statistics

External funding

Knut and Alice Wallenberg Foundation

Project description

Industrial robots, autonomous cars, stocks trading algorithms, and deep network assisted evaluation of medical images all crucially involve real-time, intelligent and automated decision making from complex and heterogeneous data, at ever growing scale and pace. This presents unprecedented theoretical and algorithmic challenges and opportunities for researchers in collecting and transforming data into information, predictions and intelligent decisions.

Optimization theory is vital to modern statistical learning and at the forefront of these advances, and the main objective of this position is to develop the next generation of learning theory to address the above challenges in the context of modern statistical learning, and potentially explore their applications in AI, including medical imaging, automated quality control, and self-driving cars, evaluated on both simulated and real data.

External funding