Post-Doctoral Research Visit F - M Inria-Cwi Postdoc on Robust Sequential Tests Estimation And Bandits H/F - INRIA

A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'eorce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie.
Post-Doctoral Research Visit F/M Inria-CWI Postdoc on Robust Sequential Tests, Estimation, and Bandits
Le descriptif de l'offre ci-dessous est en Anglais
Type de contrat : CDD

Niveau de diplôme exigé : Thèse ou équivalent

Fonction : Post-Doctorant

Niveau d'expérience souhaité : Jusqu'à 3 ans

A propos du centre ou de la direction fonctionnelle

Created in 2008, the Inria center at the University of Lille employs 360 people, including 305 scientists in 16 research teams. Recognized for its strong involvement in the socio-economic development of the Hauts-De-France region, the Inria center at the University of Lille maintains a close relationship with large companies and SMEs. By fostering synergies between researchers and industry, Inria contributes to the transfer of skills and expertise in the field of digital technologies, and provides access to the best of European and international research for the benefit of innovation and businesses, particularly in the region.

For over 10 years, the Inria center at the University of Lille has been 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).

Contexte et atouts du poste

Every year Inria International Relations Department has a few postdoctoral positions in order to support Inria international collaborations. The postdoctoral contract will have a duration of 12 to 24 months. The default start date is November 1st, 2026 and not later than January, 1st 2027. The postdoctoral fellow will be recruited by one of the Inria Centres in France but it is recommended
that the time is shared between France and the partner's country (please note that the postdoctoral fellow has to start his/her contract being in France and that the visits have to respect Inria rules for missions).

Mission confiée

Candidates for postdoctoral positions are recruited after the completion of their Ph.D. or a first postdoctoral period. To be eligible, candidates must have defended their Ph.D. no more than 3 years before the start date of the contract. As the start date will be between November 1, 2026 and January 1, 2027, the latest eligible Ph.D. defense date will vary accordingly (approximately between November 1, 2023 and January 1, 2024). In order to encourage mobility, the postdoctoral position must take place in a scientific environment that is truly different from the one of the Ph.D. (and, if applicable, from the position held since the Ph.D.); particular attention is thus paid to French orinternational candidates who obtained their doctorate abroad.

Deadline for application: June 7, 2026

Principales activités

The postdoc project is hosted jointly by INRIA Lille and CWI in Amsterdam. These national research centers have ongoing collaborations in the area of bandits and statistical testing. The current postdoc project revolves around the question of sequential robust estimation. This includes for example mean estimation in the Huber model with adversarial corruptions (Mathieu et al., 2022;
Agrawal et al., 2024) and A/B testing under mild model misspecification.

Robust statistics and robust estimation deal with inference and estimation when the data have outliers, i.e. a small proportion of the data is arbitrary and does not come from the distribution from which we want to learn (Ronchetti and Huber, 2009; Wilcox, 2012). As these outliers can make most classical non-robust statistics arbitrarily bad, the classical approaches of least square regression and maximum likelihood estimates have to be significantly modified. The effect of outliers is even stronger when the sample-size is small, in which case it is customary to use sequential methods to stop collection of data as soon as we have enough to conclude. Depending on when the outliers are collected, a sequential test may completely fail- stops very early and ends up with a wrong conclusion with high confidence.

More specifically, we are interested in studying two types of statistics, namely the Generalized Likelihood Ratio Test statistic (GLRT) (Kaufmann and Koolen, 2021; Agrawal et al., 2024) and the closely related KLInf statistic (Degenne and Mathieu, 2024), for the sequential setting and specific corruption models. Both these statistics are popular tools in statistical testing due to their close relation to information theoretic lower bounds on the minimal sample size needed to conclude. These statistics have already been applied successfully to estimation, confidence intervals and testing in both parametric and non-parametric models. Though the GLRT and KLinf statistics are well-defined in some of the corrupted settings (Agrawal et al., 2024), their concentrations are not sufficiently understood for most of the practical distributions.

In this context, the postdoc will work with us to resolve challenges of sequential robust estimation problem with specific distributional assumptions, structure and corruption styles. Specifically, we would work on one or more of these problems:

- Behaviour of GLRTs under different models of corruptions and structures of data distributions,

- Tightness and coverage of anytime-valid and robust confidence intervals in terms of KLInf,

- Concentration of KLInf driven robust mean estimation under corruptions beyond Gaussians.

The postdoc will study, employ and develop statistical frameworks including GLRT, KLinf, GRO and E-values (Gr¨unwald et al., 2024), martingales (Ruf et al., 2022; Kaufmann and Koolen, 2021), online learning and universal prediction (Agrawal et al., 2021).

The candidate is expected to conduct the research activities, that is bibliographical search, proposing original ideas related to the topic and developing them, presenting the work in the Scool seminar, workshops and conferences. Due to the collaborative nature of the project, the candidate is also expected to spend a part of time at CWI Amsterdam. The candidate should aim to publish the research results in premier conferences and journals of our field of research (e.g. ICML, NeurIPS, COLT, IJCAI, AAAI, JMLR, Annals of Stat.). Since the work involves and impacts responsible AI in general, the successful candidate should collaborate in writing scientific articles aiming towardsthe larger audience.

References

Agrawal, S., Koolen, W. M., and Juneja, S. (2021). Optimal best-arm identification methods for tail-risk measures. Advances in neural information processing systems, 34:25578-25590.

Agrawal, S., Mathieu, T., Basu, D., and Maillard, O.-A. (2024). Crimed: Lower and upper bounds on regret for bandits with unbounded stochastic corruption. In International Conference on Algorithmic Learning Theory, pages 74-124. PMLR.

Degenne, R. and Mathieu, T. (2024). Information lower bounds for robust mean estimation.

Grunwald, P., de Heide, R., and Koolen, W. (2024). Safe testing. Journal of the Royal Statistical Society. Series B: Statistical Methodology, 86(5):1136-1137.

Kaufmann, E. and Koolen, W. M. (2021). Mixture martingales revisited with applications to sequential tests and confidence intervals. The Journal of Machine Learning Research, 22(1):11140-11183.

Mathieu, T., Basu, D., and Maillard, O.-A. (2022). Bandits corrupted by nature: Lower bounds on regret and robust optimistic algorithms. Transactions on Machine Learning Research.

Ronchetti, E. M. and Huber, P. J. (2009). Robust statistics. John Wiley & Sons Hoboken, NJ, USA.

Ruf, J., Larsson, M., Koolen, W. M., and Ramdas, A. (2022). A composite generalization of Ville's martingale theorem. arXiv preprint arXiv:2203.04485.

Wilcox, R. R. (2012). Introduction to robust estimation and hypothesis testing. Academic press.

Compétences

The candidate should preferably have the following skills:

- A strong background in mathematics/statistics
- A good knowledge of machine learning, statistics, and algorithms
- Broad interest for robust statistics and/or hypothesis testing
- Knowledge of programming languages such as Python, Julia
- Some experience with implementation and experimentation (a plus)
- A good command of English

Please follow the instructions given in https://team.inria.fr/magnet/how-to-apply/ to set up your application file. In brief, the application of the candidate should include his/her CV, an application letter, (two or more) recommendation letters, and the school transcripts. It is reccommended that the candidate contacts Debabrota Basu, Timothee Mathieu, and Wouter Koolen while preparing the application.

Avantages

- 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

Rémunération

2 788 € Monthly Gross Salary