Lyudmila Grigoryeva
1 week ago
Postdoctoral Researcher in Statistical Learning Theory, Kernel Methods, and Random Features at University of St.Gallen University of St.Gallen in Switzerland
Degree Level
Postdoc
Field of study
Computer Science
Funding
The postdoctoral position runs from 1 October 2026 to 31 August 2027 (11 months) at 75% employment. It is funded through the project and is intended as a stepping stone toward an SNSF Project Funding proposal. Additional funding and the possibility of continuing the position may become available if the funding proposal is successful.
Country
Switzerland
University
University of St. Gallen
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.
Apply for this position
Keywords
Suggested positions
About this position
Lyudmila Grigoryeva, Associate Professor at the University of St.Gallen (School of Economics and Political Science, SEPS-HSG), is recruiting a postdoctoral researcher for a project at the intersection of statistical learning theory, nonparametric inference, kernel methods, and random weight neural networks.
The research topics include statistical inference for kernel and random-feature ridge regression; finite-sample and asymptotic theory for random-feature sieves; covariance kernels and RKHS theory; connections between random features, random weight neural networks, and reservoir computing; sequential and reservoir (Volterra) kernels; random projections (sketching) and scalable kernel methods including MMD; and applications to financial and macroeconomic time series.
The position starts on 1 October 2026 and ends on 31 August 2027 (11 months, 75% appointment). It is funded through the project and is intended as a stepping stone toward an SNSF Project Funding proposal. If the funding proposal is successful, additional funding and the possibility of continuing the position may become available.
Applicants should have a strong theoretical background in statistics, probability, machine learning theory, applied mathematics, econometrics, or a related field. Experience with nonparametric statistics, asymptotic theory, empirical processes, kernel methods, random features, or neural-network theory is especially relevant. By the start date, candidates must have obtained their PhD within the previous two years (on or after 1 October 2024). Work permit approval is required where applicable.
To apply, send a CV and a short description of your research interests directly to the announcer by email. Informal enquiries are welcome.
Funding details
The postdoctoral position runs from 1 October 2026 to 31 August 2027 (11 months) at 75% employment. It is funded through the project and is intended as a stepping stone toward an SNSF Project Funding proposal. Additional funding and the possibility of continuing the position may become available if the funding proposal is successful.
What's required
Candidates should have a strong theoretical background in statistics, probability, machine learning theory, applied mathematics, econometrics, or a related field. Relevant experience includes nonparametric statistics, asymptotic theory, empirical processes, kernel methods, random features, or neural-network theory. By 1 October 2026, applicants must have obtained their PhD within the preceding two years (on or after 1 October 2024). For candidates requiring a work permit, appointment depends on the permit being granted.
How to apply
Send your CV and a short description of your research interests to the announcer's email. Informal enquiries are welcome.
More information can be found here
Ask ApplyKite AI
Professors
How do I apply for this?
Sign in for free to reveal details, requirements, and source links.