PhD positions: Sequential and adaptive learning under dependence and non-standard objective functions (PIs: Blanchard/Carpentier) at Institut of Mathematics, University of Magdeburg
The DFG-funded Collaborative Research Center SFB 1294 “Data Assimilation – The Seamless
Integration of Data and Models”, hosted at the University of Potsdam jointly with its partner
Institutions HU Berlin, TU Berlin, Universität Magdeburg, WIAS Berlin and GFZ Potsdam,
invites applications for a doctoral position available from January 1st, 2018, or later.
The assimilation of time-dependent data sets into complex evolution models lead to unique mathematical and computational challenges, which provide the central theme of SFB 1294. Data assimilation is a newly emerging field, which lies at the confluence of several established research areas in mathematics and statistics on the one hand and application areas such as geosciences on the other. Our vision is to establish a rigorous mathematical
underpinning of data assimilation, to develop principled computational methodologies, and to apply these methodologies to emerging application fields in the geosciences, neurosciences and biophysics. SFB 1294 provides a fantastic research infrastructure including a large interdisciplinary network of researchers, its own graduate school, and funding opportunities for conference visits, summer schools, hosting international experts etc. SFB 1294 strives to increase the proportion of women in research. People with an immigration background are specifically encouraged to apply.
We seek applicants for a doctoral position (E13 75%) within Project A03: Sequential and adaptive learning under dependence and non-standard objective functions
This PhD position will be located mainly in the Otto von Guericke University of Magdeburg.
This project is concerned with the problem of learning sequentially, adaptively and in partial information on an uncertain environment. In this setting, the learner collects sequentially and actively the data, which is not available before-hand in a batch form. As a motivating example, consider the problem of sequential and active attention detection through an eye tracker. A human user is looking at a screen, and the objective of an automatized monitor (learner) is to identify through an eye tracker zones of this screen where the user is not paying sufficient attention. In order to do so, the monitor is allowed to flash a small zone in the screen, e.g. light a pixel (action), and the eye tracker detects through the eye movement if the user has observed this flash. Ideally the monitor should focus on these difficult zones and flash more often there (i.e. choose more often specific actions corresponding to less identified zones). Therefore, sequential and adaptive learning methods are expected to improve the performances of the monitor.
The PhD candidate will focus on developing sequential learning algorithms with mathematical guarantees for learning on given non-stationary processes that are relevant in the context of recommendation systems, and on implementation of the algorithms that will be developed. S/He will also work on the eye tracker based application of the project. A degree in machine learning or in mathematics with an interest in theoretical computer science will be preferred. The salary is determined by the collective bargaining agreement for public employees in Germany (TV-L 13 Ost). All positions are temporary in accordance with Section 2 subsection 1 of the Academic Fixed-Term Contract Law (WissZeitVG). The position requires completed academic studies at an institute of higher learning (Master degree or equivalent). This PhD position will be located mainly in the Otto von Guericke University of Magdeburg. Under the laws of the federal state of Sachsen Anhalt, employees under this contract are permitted to dedicate at least 25% of their contract time for their scientific qualification. The Otto von Guericke University of Magdeburg strives to maintain gender balance among its staff. Severely disabled applicants shall receive preference in case of equal qualifications. We expressly invite applications from people with migration backgrounds.
Please send your application as a single PDF including:
(1) a statement of research interests and motivation,
(2) a full CV,
(3) the names and e-mail addresses of at least two referees,
(4) academic transcripts,
(5) list of publications/talks/presentations, and, if applicable,
(6) a link to a copy of the master’s or PhD thesis
to SFB1294@uni-potsdam.de. Please clearly indicate in the subject line, which of the projects/positions you are applying for (e.g., “A03”).