PhD Position F/M Responsible Reinforcement Learning: Robustness and Privacy in and by Sequential Decision Making
Il y a 6 mois
Contexte et atouts du poste
In his/her journey to the doctoral thesis, the candidate will be supported by PEPR project FOUNDRY, and supervised by . Debabrota and Emilie are affiliated with the
As RL algorithms are getting deployed in real-life the questions of responsible deployment, such as robustness to noise and perturbation to the feedback from environment, and privacy if users are involved in the environment yielding data.
Our works have shown that for structure-less and linear settings of multi-armed bandits and active testing (aka pure exploration) imposing privacy yields two regimes of performance. For the regime used in practice, privacy can be preserved without loss of utility. But our existing approach is not directly applicable to more practically appealing settings of RL, like MDPs or bandits with side-information (aka contexts). In these settings, there is a gap between achievable performances and the algorithms. Thus, we want to study whether the cost of privacy in contextual bandits and MDPs, and also to design optimal, computationally efficient algorithms.
Similarly, we have studied impact of unbounded corruption in feedback and safety constraints in stochastic multi-armed bandits and active testing (aka pure exploration). We want to understand how do they impact more structured RL problems and how can we design optimal algorithms in these setting.
The project is expected to simulate the existing and new collaborations with researchers and groups working on privacy-preserving machine learning, robustness, adaptive testing, and reinforcement learning. In future, the candidate will be encouraged to not only work with us but collaborate internationally. The candidate will also be part of the
Mission confiée
This position is entirely dedicated to do one's Ph.D. thesis. French rules put a strong emphasis on the fact that the Ph.D. is completed within 3 full years of studies.
It is also possible to teach up to a reasonnable amount of time per year (say 30 hours / year to give a rough idea of what we mean by "reasonable"). More details about the topic of the Ph.D. is available at
Principales activités
All research activities, that is bibliographical search, proposing original ideas related to the topic of the Ph.D. and developing them, presenting the work in the Scool seminar, workshops and conferences. 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). Since the work involves and impacts the responsible AI in general, the successful candidate should collaborate in writing scientific articles aiming towards the larger audience.
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 differential privacy and robustenss Knowledge of programming languages such as Python. C/C++ Some experience with implementation and experimentation (a plus) A good command of EnglishPlease follow the instructions given in 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 and Emilie while preparing the application.
The deadline for application is 15th July, 2024.
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
1st and 2nd year : 2100 € (gross monthly salarye)
3rd year : 2190 € (gross monthly salary)
-
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste In his/her journey of postdoc, the candidate will be supported by . Debabrota is affiliated with the The candidate is expected to work on understanding impact of different types of constraints and structures on the performance and design of bandit and RL algorithms. The project is expected to simulate the existing and...
-
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste This PhD student position will be supported by the project. While this position will be in the MAGNET team in Lille, we will collaborate with the several European project partners. While AI techniques are becoming ever more powerful, there is a growing concern about potential risks and abuses. As a result, there has been...
-
Villeneuve-d'Ascq, France Inria Temps plein_Le descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat**: CDD **Niveau de diplôme exigé**: Bac + 5 ou équivalent **Fonction**: Doctorant **Niveau d'expérience souhaité**: Jeune diplômé **A propos du centre ou de la direction fonctionnelle**: The Inria University of Lille centre, created in 2008, employs 360 people including 305...
-
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste This engineer position will be supported by the project. While this position will be in the MAGNET team in Lille, we will collaborate with the several European project partners. While AI techniques are becoming ever more powerful, there is a growing concern about potential risks and abuses. As a result, there has been an...
-
Temporary scientific engineer
Il y a 7 mois
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste This engineer position will be supported by the CAPS'UL project. The position will be based in the MAGNET team in Lille, in very close collaboration with the Lille Hospital. The CAPS'UL project objective is to promote digital health culture for current and future healthcare professionals. Part of the project concerns the...
-
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste This post-doctoral position will be supported by the project. While this position will be in the MAGNET team in Lille, we will collaborate with the several European project partners. While AI techniques are becoming ever more powerful, there is a growing concern about potential risks and abuses. As a result, there has...
-
Phd Position F/m Ecological and Economic Logistics
Il y a 3 mois
Villeneuve-d'Ascq, France Inria Temps pleinLe descriptif de l’offre ci-dessous est en Anglais_ **Type de contrat **:CDD **Niveau de diplôme exigé **:Bac + 5 ou équivalent **Fonction **:Doctorant **A propos du centre ou de la direction fonctionnelle**: The Inria University of Lille centre, created in 2008, employs 360 people including 305 scientists in 15 research teams. Recognised for its...
-
Villeneuve-d'Ascq, Hauts-de-France Inria Temps pleinWe are seeking a highly skilled Data Scientist to join our team at Inria University of Lille centre. As a Data Scientist, you will play a key role in the development of the open-source library DecLearn for private and decentralized/federated machine learning and data analysis.Job DescriptionThe successful candidate will be responsible for consolidating and...
-
Phd in Resource Allocation for Energy Sobriety in
Il y a 3 mois
Villeneuve-d'Ascq, France IMT Nord Europe Temps plein**PhD in Resource allocation for energy sobriety in secure wireless communication systems impaired by nonlinearities**: - Réf **ABG-126120** - Sujet de Thèse- 04/10/2024- Contrat doctoral- IMT Nord Europe- Lieu de travail- Villeneuve d'Ascq - Les Hauts de France - France- Intitulé du sujet- PhD in Resource allocation for energy sobriety in secure...
-
Villeneuve-d'Ascq, Hauts-de-France Inria Temps pleinJob OverviewWe are seeking a highly skilled Machine Learning Engineer for Private and Decentralized Healthcare to join our team at Inria University of Lille. As a key member of our research team, you will be responsible for developing and implementing decentralized machine learning algorithms for medical studies.The ideal candidate will have strong...
-
Decentralized Machine Learning Developer for Medicine
il y a 1 semaine
Villeneuve-d'Ascq, Hauts-de-France Inria Temps pleinAbout the ProjectThe DecLearn project is an open-source library developed by the INRIA-MAGNET team in collaboration with the Lille Hospital. The goal of this project is to create a decentralized and privacy-preserving machine learning framework for multi-centric medical studies.As a Private and Federated Machine Learning Specialist, you will play a crucial...
-
Engineer on private and decentralized machine learning for medicine
il y a 2 semaines
Villeneuve-d'Ascq, Nord, France Inria Temps pleinA propos du centre ou de la direction fonctionnelle 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...
-
Villeneuve-d'Ascq, France Institut Mines-Télécom Temps plein**Discipline**:Wireless communication **Line Manager**: Laurent Clavier, Yahia Medjhadi **Workplace**:IMT Nord Europe, Villeneuve d’Ascq **Type of contract and duration**:Post-doc, 18 months **CONTEXT**: Public establishment belonging to IMT (Institut Mines-Télécom), placed under the supervision of the Ministry of Economy, Finance and Industrial and...
-
Villeneuve-d'Ascq, France IMT Nord Europe Temps pleinPublic establishment belonging to IMT (Institut Mines-Télécom), placed under the supervision of the Ministry of Economy, Finance and Industrial and Digital Sovereignty, IMT Nord Europe has three main objectives: providing our students with ethically responsible engineering practice enabling them to solve 21st century issues, carrying out our R&D activities...
-
Villeneuve-d'Ascq, France Institut Mines-Télécom Temps pleinDiscipline: Wireless communicationLine Manager: Laurent Clavier, Yahia MedjhadiWorkplace: IMT Nord Europe, Villeneuve d'AscqType of contract and duration: Post-doc, 18 monthsCONTEXT:Public establishment belonging to IMT (Institut Mines-Télécom), placed under the supervision of the Ministry of Economy, Finance and Industrial and Digital Sovereignty, IMT...
-
Postdoctoral Position Offer: Hybrid Beamforming
Il y a 3 mois
Villeneuve-d'Ascq, France Institut Mines-Télécom Temps plein**Unit **:Centre for Digital Systems **Line Manager**: Sylvain Lecomte **Type of contract and duration **:Fixed term contract - 18 months **Workplace**: Villeneuve d’Ascq **CONTEXT**: Public establishment belonging to IMT (Institut Mines-Télécom), placed under the supervision of the Ministry of Economy, Finance and Industrial and Digital Sovereignty,...
-
Senior Research Engineer
il y a 2 semaines
Villeneuve-d'Ascq, Hauts-de-France Institut Mines-Télécom Temps pleinJob Summary:We are seeking a highly skilled Senior Research Engineer to join our team at Institut Mines-Télécom Nord Europe. The successful candidate will be responsible for investigating state-of-the-art hybrid beamforming schemes for sub-THz communication, designing phase-noise-resilient hybrid beamforming schemes, and integrating proposed HB schemes...
-
Senior Machine Learning Engineer for Decentralized Medicine
il y a 1 semaine
Villeneuve-d'Ascq, Hauts-de-France Inria Temps pleinAbout the JobInria, a leading French research institute in digital sciences, seeks a Senior Machine Learning Engineer to join its INRIA-MAGNET team at the University of Lille. As part of this role, you will work on developing an open-source library for private and decentralized machine learning, focusing on multi-centric medical studies across several...
-
Private Machine Learning Engineer for Medicine
il y a 6 jours
Villeneuve-d'Ascq, Hauts-de-France Inria Temps pleinAbout the JobWe are seeking a Private Machine Learning Engineer for Medicine to join our team at Inria University of Lille centre. As a key member of our research team, you will play a crucial role in developing open source libraries for private and decentralized machine learning. Your primary responsibility will be to consolidate and extend the existing...
-
Machine Learning Engineer for Decentralized Medical Studies
il y a 2 semaines
Villeneuve-d'Ascq, Hauts-de-France Inria Temps pleinJob SummaryWe are seeking a skilled Machine Learning Engineer to join our team at Inria, working on a project with the Lille Hospital to develop an open-source library for private and decentralized machine learning. The successful candidate will consolidate and extend the existing library, integrate it into partner hospitals' information systems, deploy it...
