Post-Doctoral Research Visit F/M Bandits and adaptive testing with scarce data

Contract type : Fixed-term contract

Level of qualifications required : PhD or equivalent

Fonction : Post-Doctoral Research Visit

About the research centre or Inria department

The  Inria University of Lille centre, created in 2008, employs 360 people  including 305 scientists in 15 research teams. Recognised for its strong  involvement in the socio-economic development of the Hauts-De-France  region, the Inria University of Lille centre pursues a close  relationship with large companies and SMEs. By promoting synergies  between researchers and industrialists, Inria participates in the  transfer of skills and expertise in digital technologies and provides  access to the best European and international research for the benefit  of innovation and companies, particularly in the region.For more  than 10 years, the Inria University of Lille centre has been located at  the heart of Lille's university and scientific ecosystem, as well as at  the heart of Frenchtech, with a technology showroom based on Avenue de  Bretagne in Lille, on the EuraTechnologies site of economic excellence  dedicated to information and communication technologies (ICT)

Assignment

The goal of the project is to design and study bandit algorithms for testing problems with scarce data, as part of the FATE ANR project https://anr.fr/Project-ANR-22-CE23-0016 .

Testing is the process of gathering observations about an unknown system (for example a new drug and a placebo) in order to answer a question (e.g. which treatment is more efficient). Good testing protocols are such that the test can be stopped after few observations, while obtaining a correct answer with high probability.

In applications where a large number of observations is available, like online advertising, algorithms that can adaptively change their future gathering of observations based on previously obtained information (called bandit algorithms) can be shown to stop as early as possible. In particular, they stop faster than non-adaptive algorithms.
However the guarantees on the stopping time of these methods are insufficient for applications in which the number of observations available is small, like clinical trials. Nonetheless, experimental evaluation of bandit algorithms show promising performance in that case.


The main goal of this Post-Doc project is to adapt bandit algorithms to the regime where observations are scarce and to prove that they allow faster testing than less adaptive protocols.

Main activities

  • Review and follow the existing literature on bandit identification and adaptive testing.
  • Theoretically and empirically study the performance of existing bandit algorithms in testing tasks with scarce data.
  • Propose new testing methods and provide theoretical and experimental evaluations of their merits.
  • Publish and present results in top machine learning conferences and journals.

Skills

A good candidate will have the following skills:

  • A strong background in theoretical machine learning and statistics
  • A good command of English
  • Experience with implementation and experimentation
  • A good knowledge of bandits algorithms or statistical hypothesis testing

Benefits package

  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage