Umeå University, Mathematics and Mathematical Statistics

scholarship ID:

2216-POSTDOC4 [#28156]

scholarship Title:

Postdoctoral scholarship (2 years) in Deep Learning for High-Dimensional Optimal Stopping and Stochastic Control

scholarship Type:

Postdoctoral

scholarship Location:

Umea, Vasterbottens Lan 901 03, Sweden

Subject Area:

Financial Mathematics

Appl Deadline:

2026/05/31 23:59:59 (posted 2026/02/23, listed until 2026/05/31)

scholarship Description:

The Department of Mathematics and Mathematical Statistics at Umeå University is offering a postdoctoral scholarship within the project “Deep Learning for High-Dimensional Joint Optimal Stopping and Stochastic Control Problems with Applications in Finance”. The scholarship is full-time for two years, with a starting date of 1 September 2026 or by agreement.

The Department of Mathematics and Mathematical Statistics conducts research in applied and theoretical mathematics, including computational methods and financial mathematics. The successful candidate will be associated with a growing research environment in applied stochastic control, deep learning, and quantitative finance, and will have opportunities for collaboration within the department as well as with national and international partners.

Project description: Many real-world decision-making problems involve both continuous control decisions and the choice of an optimal stopping time. Examples arise naturally in finance, forestry, agriculture, and aquaculture, where decisions about investment, treatment, feeding, or harvesting must be made under uncertainty. While optimal stopping and stochastic control problems have been studied extensively on their own, numerical methods for joint problems in high-dimensional settings remain a major scientific challenge.

The central aim of this project is to advance the understanding and solution of high-dimensional joint optimal stopping and stochastic control problems using modern mathematical and computational techniques. These problems are closely connected to Hamilton–Jacobi–Bellman variational inequalities (HJB-VIs), which provide a unifying theoretical framework but quickly become intractable with classical methods as the dimension increases.

The project offers three complementary scientific directions through which these challenges can be addressed:

1. PDE and analytical methods, focusing on the theory and properties of HJB variational inequalities combined with physics-informed neural networks (PINNs); 2. Deep Reinforcement Learning, where learning-based algorithms are used to approximate optimal policies and stopping strategies; 3. Forward–Backward (reflected) stochastic differential equation (F(R)BSDE) solvers, which provide probabilistic representations and numerical methods suitable for high-dimensional settings.

A key feature of the project is its flexibility: the precise focus and methodological approach will be adapted to the expertise, background, and scientific interests of the postdoctoral scholarship holder. The project is designed to allow the scholarship recipient to deepen existing strengths while developing new skills at the interface of (stochastic) analysis, numerical methods, and machine learning.

The postdoctoral researcher will have the opportunity to:

- pursue research along one or more of the three methodological directions described above, - deepen their understanding of joint optimal stopping and stochastic control problems, - apply developed methods to financially motivated and resource-management applications, - collaborate with researchers within and beyond the department, such as AquaRisk (https://www.ntnu.edu/aquarisk/), - disseminate results through publications and participation in international conferences and workshops.

This postdoctoral scholarship is financed and administered by the Kempe Foundation. The stipend is tax-free and will be 750 000 SEK for two years, meaning 375 000 SEK per year.

Umeå provides outstanding working and living conditions. This youthful city is situated beside a large river, surrounded by forests and lakes, and is near the sea. The area offers numerous opportunities for both indoor and outdoor activities.

We are not accepting applications for this job through MathJobs.Org right now. Please apply at https://www.umu.se/en/work-with-us/postdoctoral-scholarships/postdoctoral-scholarship-2-years-in-deep-learning-for-high-dimensional-optimal-stopping-and-stochastic-control_900883/ .

Contact: Kevin Kamm

Email: email address

Postal Mail:

: Department of Mathematics and Mathematical Statistics
Linneaus väg 49
901 87 Umeå
SWEDEN

Web Page: https://www.umu.se/en/department-of-mathematics-and-mathematical-statistics/