Loading...
 

Job Ad Display

Return to the list

post-doc: Postdoctoral researcher: multiobjective optimization and decision support in well-being
Where: University of Jyvaskyla, Finland Finland
What: We are recruiting a post-doctoral researcher for 1-3 years to work at the Faculty of Information Technology (https://www.jyu.fi/en/it), University of Jyvaskyla (https://www.jyu.fi/en) in Finland as a member of the Multiobjective Optimization Group (http://www.mit.jyu.fi/optgroup) in close collaboration with the JYU.Well community https://www.jyu.fi/en/research/jyuwell-school-of-wellbeing/jyuwell-research-spearheads/jyuwell-profiling-area-2023-2028. The application deadline is February 21, 2024. For more information, see https://ats.talentadore.com/apply/postdoctoral-researcher-jyu-well/8RboLr
Applications are to be submitted via the online application system (button at the top of the above-mentioned page).

The focus of the recruited post-doctoral researcher will be devoted to applications of wellbeing with the help of methods of multiobjective optimization and decision analytics. An example of our publications giving an example of the field is https://doi.org/10.1080/07853890.2021.2024876. If you are recruited in this postdoctoral position, you will have excellent collaboration networks with both experts in the Multiobjective Optimization Group and the JYU.Well community and access to e.g. various types of data. Our mission is not only to understand data and make forecasts based on data but make optimized recommendations and decisions based on the data. In making good decisions, we take multiple conflicting objective functions into account simultaneously – thus we support a decision maker or decision makers in finding the best balance among the conflicting objective functions by augmenting data with domain expertise of decision makers. This is a unique opportunity to work with problems that really matter.

We welcome new, talented members to the Multiobjective Optimization Group. The Group works on multiobjective optimization as well as decision/prescriptive analytics and data-driven/data-enabled optimization. We develop methods for supporting decision making in the presence of multiple conflicting objective functions. Therefore, knowledge of multiobjective optimization is required. To be a bit more specific, the group develops methods as well as software and works with various applications of multiobjective optimization. We specialize on interactive multiobjective optimization methods (both scalarization-based and evolutionary methods and their hybrids). We are interested in supporting a single decision maker as well as groups of decision makers. We also develop visualizations and apply artificial intelligence, machine learning tools and explainability as a part of the decision support processes. We are developing an open source software framework DESDEO for interactive multiobjective optimization methods (desdeo.it.jyu.fi). Furthermore, we are actively involved in a thematic research area called Decision Analytics utilizing Causal Models and Multiobjective Optimization (DEMO, jyu.fi/demo) where the objective is to support data-driven decision making. The open position is connected to this – developing tools for data-driven or data-enabled decision support with e.g. wellbeing, health and rehabilitation as examples of applications.

The postdoctoral researcher's duties focus on internationally high-level research in the focus areas of the JYU.Well profiling area 2023-2028 | University of Jyväskylä. The duties include supporting the interdisciplinary development of wellbeing research and activities, and participating in acquiring external funding. The postdoctoral researcher is also expected to participate in societal interaction together with the JYU.Well research community, supervising students and in teaching within their own areas of expertise. The amount of teaching duties is rather small. Rather recently graduated researchers with a doctoral degree relevant to these areas are most welcome to apply! For more, see the call for applications.

For information about application guidelines and a link to the electronic application system, see https://ats.talentadore.com/apply/postdoctoral-researcher-jyu-well/8RboLr

Please, forward this announcement to those who might be interested in the positions. Do not hesitate to contact me if you have questions!

With best regards, Kaisa Miettinen

************************************
Professor Kaisa Miettinen, PhD
University of Jyvaskyla
Multiobjective Optimization Group: http://www.mit.jyu.fi/optgroup/
Faculty of Information Technology, P.O. Box 35 (Agora)
FI-40014 University of Jyvaskyla, Finland
- - -
  • Director of the thematic research area Decision Analytics utilizing Causal Models
and Multiobjective Optimization, http://www.jyu.fi/demo
- - -
tel. +358 50 3732247 (mob.)
email: kaisa.miettinen at jyu.fi
homepage: http://www.mit.jyu.fi/miettine and http://www.mit.jyu.fi/miettine/engl.html
My book: Nonlinear Multiobjective Optimization, Kluwer (Springer): http://www.mit.jyu.fi/miettine/book/


Who: Prof. Kaisa Miettinen; kaisa.miettinen@jyu.fi (multiobjective optimization); Research Director Katja Kokko, katja.r.kokko@jyu.fi (JYU.Well)
When: Until 2024-02-21 16:59
Presented at next GECCO?: no

PhD: PhD in Heterogenous Bayesian Optimization
Where: Manchester , United Kingdom United Kingdom
What: About the Project
The UKRI AI Centre for Doctoral Training (CDT) in Decision Making for Complex Systems is a joint CDT between the University of Manchester and the University of Cambridge. The CDT provides funding for four years of advanced studies towards a PhD. The first year consists of a taught program at Manchester that will cover the fundamentals of Machine Learning. This year is followed by three years of research at either at Manchester or Cambridge. Please note the research element of the PhD will take place at the host institution of the supervisor listed for each project.

This is a collaborative project with Honda Research Institute (HRI) Europe https://www.honda-ri.de/, the research arm of Honda, one of the world's largest and well-known automotive companies. Efficient and sustainable vehicle design is one of HRI’s focus areas. A typical challenge here is performing costly simulations (eg through CFD), potentially combined with resource-intense physical experiments in the laboratory, resulting in optimization problems with heterogeneous objectives and/or constraints 1. Heterogeneous objectives/constraints may differ eg in practical evaluation effort (time, costs, resources, etc), formal computational complexity, determinism (stochastic vs deterministic), or some combination of all these. A particularly challenging variety of heterogeneity may occur by the combination of a time-consuming laboratory-based objective/constraint with other objectives/constraints that are evaluated using faster computer-based calculations 2,3.

Current research on heterogeneous objectives is largely focused on problems with two objectives (typically one slow vs one fast to evaluate objective) 1. Research on heterogeneous constraints is even more so in its infancy. Also, most existing research has only considered heterogeneity in terms of computational time of objectives/constraints.

In this PhD project, we propose to generalize recent advances in machine learning and operations search 1,4 to tackle optimization problems with heterogeneous objectives/constraint. Hybrid methods will be developed and validated on real problems provided by HRI. Furthermore, realistic synthetic benchmark problems will be proposed varying in type and level of heterogeneity. The outcome of this research will allow tackling heterogenous optimization problems more efficiently while using less resources.

For queries regarding the project, please email Richard Allmendinger (richard.allmendinger@manchester.ac.uk) and Mauricio Alvarez (mauricio.alvarezlopez@manchester.ac.uk)

For queries regarding the AI Centre for Doctoral Training (CDT) in Decision Making for Complex Systems, please email ai-decisions-cdt at manchester.ac.uk.

Entry requirements

Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.
Background in probabilistic GPs, Optimization, Multi-Criteria Decision Making. Previous experience in Bayesian Optimisation would be great.

English language requirements (for international/EU candidates)

You have must have one or more of the following:

IELTS test minimum scores - 7.0 overall, 6.5 other sections.
TOEFL (internet based) test minimum scores - 100 overall, 25 in all sections.
Pearson Test of English (PTE) UKVI/SELT or PTE Academic minimum scores - 76 overall, 76 in writing, 70 in other sections.
To demonstrate that you have taken an undergraduate or postgraduate degree in a majority English speaking nation within the last 5 years.
Other tests may be considered.
How to Apply:

As the CDT has only recently been awarded we encourage you to contact the supervisor of the project you are interested in with your CV and supporting documents. You will have a chance to meet with prospective supervisors prior to submitting an application - further details will be provided.

Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact.

We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.

Funding Notes
Funding includes tuition fees and stipend at the UKRI minimum rate, currently £18,622/annum (see View Website for further information). Studentship funding is for 4 years commencing 1 October 2024. This scheme is open to both the UK and international applicants. We are only able to offer a limited number of scholarships to applicants outside the UK.
References
1 Allmendinger, R., Handl, J. and Knowles, J., 2015. Multiobjective optimization: When objectives exhibit non-uniform latencies. European Journal of Operational Research, 243(2), pp.497-513.
2 Allmendinger, R. and Knowles, J., 2023. Heterogeneous objectives: state-of-the-art and future research. In Many-Criteria Optimization and Decision Analysis: State-of-the-Art, Present Challenges, and Future Perspectives (pp. 317-335). Cham: Springer International Publishing.
3 Blank, J. and Deb, K., 2022. Handling constrained multi-objective optimization problems with heterogeneous evaluation times: proof-of-principle results. Memetic Computing, 14(2), pp.135-150.
4 Moreno-Muñoz, P., Artés, A. and Alvarez, M., 2018. Heterogeneous multi-output Gaussian process prediction. Advances in neural information processing systems, 31.

Who: Richard Allmendinger, richard.allmendinger@manchester.ac.uk
When: Until 2024-03-31 01:00
Presented at next GECCO?: yes



Return to the list