PhD Candidate on Robust Best Arm Identification

PhD Candidate on Robust Best Arm Identification

The Faculty of Science, the Mathematical Institute, and the Leiden Institute of Advanced Computer Science are looking for a:

PhD Candidate on Robust Best Arm Identification

We are looking for a motivated candidate on robust best arm identification and, more broadly, online learning. This research field lies at the intersection of mathematical machine learning and learning theory, which both have, as one of the fundamental research questions, to identify the best possible action one can take. While an unlimited source of information would always allow for identifying the optimal action, most real-world scenarios start with little or no prior information. The question then becomes: what is the fastest way to obtain relevant information to identify the best action? We will use techniques from online learning to address this problem.

The best arm identification problem involves identifying the best action based on sequential feedback. In the bandit model, we query actions and receive feedback only about the queried action. For instance:

• A farmer wants to find which rice variety yields best in Dutch polders, receiving feedback only for the variety planted.
• In A/B testing, a web designer tests two website versions, with feedback only on the live version.

Feedback is often assumed to be stochastic, meaning outcomes follow a probability distribution. For example, the rice yield may have a fixed distribution, allowing estimation of the best variety over time. However, in adversarial settings where feedback is manipulated, simple estimation fails, and robust algorithms are needed to handle such challenges. This is precisely the problem we aim to tackle within this PhD project, which focuses on developing robust algorithms for best arm identification under adversarial conditions. If successful, this project will lead to a line of research in different applications. For example, in Bayesian optimization, best x% arm identification, and bandit logistic regression.

The execution of the research will be highly participatory. You will spend time at the Faculty of Science offices, particularly in the statistical science group in the mathematical institute and the natural computing cluster within the Leiden Institute of Advanced Computer Science. You will collaborate with faculty and fellow motivated PhD students within the groups.

Key responsibilities

• Conduct original and novel research in the field of best arm identification and online learning;
• Publish and present scientific articles at international journals and conferences;
• Active communication with other PhD candidates and members in the statistical science group and natural computing cluster.
• On-site presence (90% of working time) to facilitate spontaneous interactions with supervisors and colleagues and foster a vibrant and engaged community within the office space;
• Assist in relevant teaching activities;

Selection Criteria
The successful applicant should be a motivated university graduate who is a top performer among his/her peers and has an excellent education and/or research track record proven by relevant experience, publications, etc. The applicant is expected to have:

• MSc degree in Mathematics, Artificial Intelligence, Data science, Computer science, or related field;
• A strong mathematical background;
• Good programming skills in e.g., Python and R;
• Experience in Machine Learning and/or gradient-free optimization;
• Excellent written and oral communication skills in English, Dutch proficiency or willingness to learn is a plus;
• Ability to work with diverse stakeholders, e.g., mathematicians, computer scientists;

Research at our faculty

The Faculty of Science is a world-class faculty where staff and students work together in a dynamic international environment. It is a faculty where personal and academic development are top priorities. Our people are committed to expand fundamental knowledge by curiosity and to look beyond the borders of their own discipline; their aim is to benefit science, and to contribute to addressing the major societal challenges of the future.

The research carried out at the Faculty of Science is very diverse, ranging from mathematics, information science, astronomy, physics, chemistry and bio-pharmaceutical sciences to biology and environmental sciences. The research activities are organized in eight institutes. These institutes offer eight bachelor’s and twelve master’s programs. The faculty has grown strongly in recent years and now has more than 2,800 staff and almost 6,000 students. We are located at the heart of Leiden’s Bio Science Park, one of Europe’s biggest science parks, where university and business life come together.

Terms and conditions
We offer a full-time 1-year term position for initially one year. After a positive evaluation of the progress of the thesis, personal capabilities and compatibility the appointment will be extended by a further three years. Salary ranges from € 2,901 to € 3,707 gross per month (pay scale P in accordance with the Collective Labour Agreement for Dutch Universities). Leiden University offers an attractive benefits package with additional holiday (8%) and end-of-year bonuses (8.3%), training and career development and sabbatical leave. Our individual choices model gives you some freedom to assemble your own set of terms and conditions. Candidates from outside the Netherlands may be eligible for a substantial tax break. All our PhD students are embedded in the Leiden University Graduate School of Science. Our graduate school offers several PhD training courses at three levels: professional courses, skills training and personal effectiveness. In addition, advanced courses to deepen scientific knowledge are offered by the research school.

D&I statement

Diversity and inclusion are core values of Leiden University. Leiden University is committed to becoming an inclusive community which enables all students and staff to feel valued and respected and to develop their full potential. Diversity in experiences and perspectives enriches our teaching and strengthens our research. High quality teaching and research is inclusive.

Enquiries can be made to Dr. Dirk van der Hoeven d.van.der.hoeven@math.leidenuniv.nl or Dr. Elena Raponi, e.raponi@liacs.leidenuniv.nl. Dr. Dirk van der Hoeven, Researcher