In many information processing systems but also machine learning algorithms, the system designer faces distributed decision-making problems. Since not all information is available everywhere, the decisions are taken based on the locally available information to achieve a common goal. Such decision problems have nonclassical information structure and are considered to be notoriously difficult because a general optimal design approach is missing. Quite recently the concept of coordination coding appeared in information theory. It basically describes what statistical relations can be achieved with the support of communications. Initial results show that this concept can be used to derive fundamental bounds for distributed decision-making systems. In this project we will expand those results with the goal to enhance the basic understanding as well as setting the basis for a framework for optimal designs. This new approach will lead to new fundamental insights and it might lead to solutions of long-standing fundamental problems. Moreover, it should be explored how these results can be exploited to understand better and improve machine learning algorithms.
The Information Science and Engineering Division at KTH Electrical Engineering has 12 faculty members and presently about 35 PhD students, who contribute to a high professional standard of intensive work and quality results, as well as to a friendly and open environment. The staff has a multicultural background and the working language is English. For more information see https: // www. kth.se/ise
Third-cycle subject: Electrical Engineering
Supervision: Professor Tobias Oechtering and Dr. Maël Le Treust, CNRS researcher at ETIS UMR 8051.What we offer
To be admitted to postgraduate education (Chapter 7, 39 § Swedish Higher Education Ordinance), the applicant must have basic eligibility in accordance with either of the following:
In addition to the above, there is also a mandatory requirement for English equivalent to English B/6, read more hereSelection
In order to succeed as a doctoral student at KTH you need to be goal oriented and persevering in your work. During the selection process, candidates will be assessed upon their ability to:
The successful applicant is expected to hold or to be about to receive an MSc degree in Electrical Engineering, Engineering Physics, Mathematics or similar with a strong mathematical background. A specialization in information theory is an asset.
The successful applicant should also have an outstanding academic track record, and well developed analytical and problem solving skills. We are looking for a strongly motivated person, who is able to work independently. Good command of English orally and in writing is required to publish and present results at international conferences and in international journals.
After the qualification requirements, great emphasis will be placed on personal competency.
Target degree: Doctoral degreeInformation regarding admission and employment
Only those admitted to postgraduate education may be employed as a doctoral student. The total length of employment may not be longer than what corresponds to full-time doctoral education in four years ' time. An employed doctoral student can, to a limited extent (maximum 20%), perform certain tasks within their role, e.g. training and administration. A new position as a doctoral student is for a maximum of one year, and then the employment may be renewed for a maximum of two years at a time.Union representatives
Contact information KTH's website.Doctoral section (Students' union on KTH Royal Institute of
Contact information section's website.Application
Apply for the position and admission through KTH's recruitment system. It is the applicant's responsibility to ensure that the application is complete in accordance with the instructions in the advertisement.
Applications must be received at the last closing date at midnight, CET/CEST (Central European Time/Central European Summer Time).
Applications must include:
You will find your individual essay about the Witsenhausen counterexample at https: // people.kth.se/~oech/Witsenhausen.pdfOther information
Striving towards gender equality, diversity and equal conditions is both a question of quality for KTH and a given part of our values.
For information about processing of personal data in the recruitment process please read here.
We firmly decline all contact with staffing, recruitment agencies and job ad salespersons.
Disclaimer: In case of discrepancy between the Swedish original and the English translation of the job announcement, the Swedish version takes precedence.