close

PhD in Computational Probability

Research / Academic
Delft

Description:

Markov Chain Monte Carlo (MCMC) is a probabilistic computational method which is of vital importance in data science (statistics, machine learning) as well as in the physical sciences (physics, chemistry, biology). For example, MCMC is applied for training of (deep) neural networks, as well as for the simulation of many-particle systems.

In recent years the MCMC community has developed fundamentally new algorithms in this family, based on Piecewise Deterministic Markov Processes (PDMPs). Important examples are the Zig-Zag Sampler (Bierkens et al., 2017) and the Bouncy Particle Sampler (Bouchard-Côté et al, 2017). Already these methods are showing excellent (sometimes even groundbreaking) computational efficiency. To highlight the importance of this new approach, the Dutch science foundation (NWO) has awarded the research project on this topic - funding this Phd project - with a prestigious Vidi grant. 

In order to apply these new methods in practice it is crucial to first obtain a solid theoretical understanding of these stochastic algorithms. This means delving into the mathematical properties of PDMPs and will therefore be a fascinating challenge for aspiring mathematicians with a strong interest and solid background in probability theory. The answers to the research questions in this project will contribute to guidelines on designing an optimal PDMP sampler for a given computational task. Given the theoretical nature of this project a background in stochastic processes and/or stochastic calculus is highly desirable.

Requirements:

- MSc in applied mathematics, pure mathematics or statistics

- Strong curriculum in the mathematical theory of stochastic processes

- Highly motivated

- Excellent communication skills

- Fluent in spoken and written English

Salary Benefits:

TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. An International Children’s Centre offers childcare and an international primary school. Dual Career Services offers support to accompanying partners. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.

As a PhD candidate you will be enrolled in the TU Delft Graduate School. TU Delft Graduate School provides an inspiring research environment; an excellent team of supervisors, academic staff and a mentor; and a Doctoral Education Programme aimed at developing your transferable, discipline-related and research skills. Please visit www.tudelft.nl/phd for more information.     

Work Hours:

38 - 40 hours per week

Address:

Mekelweg 2