Post-Doctoral Research Visit F/M Postdoctoral position Reinforcement Learning for Collaborative Annotation
il y a 4 semaines
Contexte et atouts du poste
This postdoctoral position is part of the national PEPR (Programme et Equipement Prioritaire de Recherche) PlantAgroEco project, coordinated by Alexis Joly. The PEPR involves several teams from various institutes (Inria ZENITH, CIRAD AMAP, CIRAD PHIM, CIRAD PBVMT, INRAE ePhytia, INRAE IGEPP, INRAE LISAH, IRD EGCE, IRD IEES, Univ. Paris Saclay, TelaBotanica). The position is funded for 18 months, and will be conducted a Inria Lille - Nord Europe under the supervision of Odalric-Ambrym Maillard. This is a postdoctoral position in Machine Learning, more specifically in Reinforcement Learning.
The starting date is flexible, it could start earlier than Feb. 1st, 2024.
Odalric-Ambrym Maillard is a researcher at Inria. He has worked for over a decade on advancing the theoretical foundations of reinforcement learning,
using a combination of tools from statistics, optimization and control, in order to build more efficient algorithms able to better estimate uncertainty, exploit structures, or adapt to some non-stationary context.
He was the PI of the ANR-JCJC project BADASS (BAnDits Against non-Stationarity and Structure) until Oct. 2021. He is also leading the Inria Action Exploratoire SR4SG (Sequential Recommendation for Sustainable Gardening) and the Inria-Japan associate team RELIANT (Reliable multi-armed bandits),
and is involved in a series of other projects, from more applied to more theoretical ones all related to the grand-challenge of reinforcement learning that is to make it applicable in real-life situations.
See \texttt{ for further details.
Scool (Sequential COntinual and Online Learning) is an Inria team-project. It was created on November 1st, 2020 as the follow-up of the team SequeL. In a nutshell, the research topic of Scool is the study of the sequential decision making problem under uncertainty. Most of our activities are related to either bandit problems, or reinforcement learning problems. Through collaborations, we are working on their application in various fields, mainly: health, agriculture and ecology, sustainable development. See our \href{ page} for more information.
Topic . Making reinforcement learning techniques applicable to real-life applications (such as the recommendation of agroecological practices in agriculture) requires overcoming several scientific bottlenecks. Within the scope of the PEPR PlantAgroEco project, this 18m postdoc will focus on providing novel reinforcement learning strategies in order to improve the collaborative annotation process of the \href{ data acquisition platform, both from a theoretical and applied perspective. This project makes appear appealing challenges around contextual multi-armed bandits relevant to collaborative decision making and recommendation at large, with a unique opportunity to interact with a real data platform used by millions. Solving the different challenges in a sound and effective way requires special attention from both mathematical and computational standpoints.
Mission confiée
The project is organized around three high-level tasks and research questions:
1. The first task is about the user annotation-expertise profile (which
may vary with features and plants): Here the goal is to
estimate it, track its evolution, and improve it.,
Regarding methods, estimation could be done actively adapting contextual bandit strategies using a form of information-driven intrinsic reward, while change-point detection and expert methods are natural to help tracking. Finally, active improvement could be done via minimal interaction, active hypothesis testing
and personalized content/task recommendation.
2. The second task is to assist the users in performing rapid annotation,
using sequential hypothesis testing personalized to their (estimated) expertise.
Here pone challenge is to get rapid annotation in a possibly non-parametric context, by adapting sample efficient hypothesis testing and best-arm identification and finite-time analysis techniques.
The short number of interactions available also suggests considering a satisficing instead of optimal regret objective. Another challenge is to personalize assistance to each user expertise, which involves contextual bandit but also contextual hypothesis testing (charting) techniques.
3. A last task is to adapt query strategies of complementary experts based for the collective labeling of existing and unknown items.
One of the challenge is to handle uncertainty of experts, building adaptive confidence sets as well as sequential tests, both parametric and non-parametric, in order to perform adaptive stopping (decide when enough labeling information has been collected) in a reliable way.
Further, experts can be complementary or disagree, which wields the challenges of enforcing diversity in the pool of experts and ensuring sound collective labeling adapting majority voting systems. Last, one may consider fairness constraints on the pool of experts to avoid a large load unbalance between experts.
These tasks can be explored in various ways and lead to other challenges but should be considered the backbone of the project. The research, though focused on the PlantNet example, should be considered from a broader perspective, and be beneficial to recommender systems at large.
Principales activités
The postdoctoral position requires a solid capacity to code, conduct relevant numerical experiments and strong analytical skills, as well as a solid background in statistics, probability, Markov chains, concentration of measure and confidence regions, a good knowledge of multi-armed bandits, especially contextual bandits, active sampling and recommender systems processes methods, and be at ease with theoretical guarantees of the considered strategies.
The successful candidate will interact both with the Scool team at Inria Lille (specialized in bandits) and the Zenith team (hosting the PlantNet application) at Inria Montpellier and more generally with the members of the PEPR project, to produce both novel publications and modules for PlantNet (with the help of the engineers from PlantNet). A good balance between theory and application is expected throughout the project.
Compétences
A PhD in machine learning or statistics, possibly related to multi-armed bandits or recommender systems.
Language: fluency in English.
Relational skills: ability to work within a group of people, listen to others, present one's work, discuss it and be able to learn from others.
While performing the assigned tasks, a certain amount of autonomy is welcome, if not necessary.
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
Gross monthly salary (before taxes) : 2 788€-
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...
-
Villeneuve-d'Ascq, France INRIA Temps pleinContexte 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, 2024 and not later than January, 1st 2025 . The postdoctoral...
-
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste Discrete optimization methods can be applied to solve a wide range of practical problems. Such problems are often formulated as either integer, or mixed-integer, programs which enables them to be solved using mathematical programming techniques. However, to this day, integer and mixed- integer programs remain extremely hard...
-
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...
-
Post-Doctoral Research Visit F/M Personalized patient follow-up
il y a 4 semaines
Villeneuve-d'Ascq, France INRIA Temps pleinContexte et atouts du poste The recruitee will join the Mission confiée The recruitee will work in close relation with both teams, Scool and the Inserm team. With Scool, the goal is to explore how the problem at hand can be modeled, most likely as a contextual bandit problem, propose algorithms, study their theoretical properties. With the...
-
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 4 semaines
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 Context This thesis is part of the French ANR project PEPR O2R (Flagship project named Organic Robotic, 37.5 Million Euros), more particularly the work-package “Softness and Sustainability” of the Structuring Action 1 (AS1) which questions the environmental impact of robotics and tries to find innovative solutions to...
-
UX Researcher
il y a 4 semaines
Villeneuve-d'Ascq, France Espace Freelance Temps pleinEspace-Freelance, réseau de consultants indépendants, recherche pour l?un de ses clients directs : un UX Researcher (H/F)Vos principales missions : Concevoir la méthodologie de recherche appropriée en fonction des besoins du projet et des utilisateurs cibles,Organisation et facilitation des tests utilisateurs,Recueillir des données qualitatives et...
-
UX Researcher
il y a 1 semaine
Villeneuve-d'Ascq, France Espace Freelance Temps pleinEspace-Freelance, réseau de consultants indépendants, recherche pour l?un de ses clients directs : un UX Researcher (H/F) Vos principales missions : Concevoir la méthodologie de recherche appropriée en fonction des besoins du projet et des utilisateurs cibles, Organisation et facilitation des tests utilisateurs, Recueillir des données qualitatives et...
-
Senior Process Technician R&D
il y a 4 semaines
Villeneuve-d'Ascq, France McCain Foods Temps plein Position Title: Senior Process Technician Position Type: Temporary - Full-Time Position Location: VilleneuvedAscq RD Grade: Grade 03 Requisition ID: 25527 At McCain, we are committed to excellence in food safety, innovation, and process optimization. We are seeking a highly skilled Senior Process Technician to...
-
Strategic Project Analyst
il y a 7 jours
Villeneuve-d'Ascq, France Mondial Relay Temps pleinCompany Description Mondial Relay, un sourire à chaque coin de rue ! Nous offrons un service d'expédition et de livraison de colis, simple, rapide, économique et vertueux, au travers un réseau de Points Relais et Lockers, créateur de liens entre e-commerçants, commerçants et consommateurs. Devenir le leader de la livraison hors-domicile en...
-
Strategic Project Analyst
il y a 7 jours
Villeneuve-d'Ascq, France Mondial Relay Temps pleinCompany Description Mondial Relay, un sourire à chaque coin de rue ! Nous offrons un service d'expédition et de livraison de colis, simple, rapide, économique et vertueux, au travers un réseau de Points Relais et Lockers, créateur de liens entre e-commerçants, commerçants et consommateurs. Devenir le leader de la livraison hors-domicile en...
-
Senior Process Technician R&D
il y a 4 semaines
Villeneuve-d'Ascq, France mccainfood Temps plein Position Title: Senior Process TechnicianPosition Type: Temporary - Full-Time Position Location: VilleneuvedAscq RD Grade: Grade 03 Requisition ID: 25527 At McCain, we are committed to excellence in food safety, innovation, and process optimization. We are seeking a highly skilled Senior Process Technician to join our team. If you...
-
Strategic Project Analyst
il y a 6 jours
Villeneuve-d'Ascq, France Mondial Relay Temps pleinJob DescriptionWe are seeking a detail-oriented and strategic thinker with project management skills to join our team as a Strategic Project Analyst. In this role, you will be responsible for reviewing business trends and market developments, conducting analysis to support business decision-making, developing strategic business plans, and managing projects...
-
Strategic Project Analyst
il y a 7 jours
Villeneuve-d'Ascq, France Mondial Relay Temps pleinJob DescriptionWe are seeking a detail-oriented and strategic thinker with project management skills to join our team as a Strategic Project Analyst. In this role, you will be responsible for reviewing business trends and market developments, conducting analysis to support business decision-making, developing strategic business plans, and managing projects...
-
Machine Learning Engineer
il y a 4 semaines
Villeneuve-d'Ascq, France Espace Freelance Temps pleinEspace-Freelance, réseau de consultants indépendants, recherche pour l?un de ses clients directs : Un Machine Learning Engineer (H/F)Votre mission :Afin d'accompagner la montée en puissance de la Generative AI, notre client recherche un LLMOps qui aura pour missions de :- Mettre en production des LLM, sous forme d'API ou sous forme de produits complets,...
-
Machine Learning Engineer
il y a 1 semaine
Villeneuve-d'Ascq, France Espace Freelance Temps pleinEspace-Freelance, réseau de consultants indépendants, recherche pour l?un de ses clients directs : Un Machine Learning Engineer (H/F) Votre mission : Afin d'accompagner la montée en puissance de la Generative AI, notre client recherche un LLMOps qui aura pour missions de : - Mettre en production des LLM, sous forme d'API ou sous forme de produits...
-
Network Engineer
il y a 4 semaines
Villeneuve-d'Ascq, France Mondial Relay Temps pleinCompany Description Mondial Relay, a smile on every street corner! We offer a simple, fast, economical and virtuous parcel shipping and delivery service, through a network of Relay Points and Lockers, creating links between e-merchants, merchants and consumers. Becoming the leader in out-of-home delivery in Europe is the challenge that our 1,400...
-
Food Service Category Leadership Manager
il y a 4 jours
Villeneuve-d'Ascq, France McCain Foods Temps pleinPosition Title: Food Service Category Leadership Manager Position Type: Regular - Full-Time Requisition ID: 29108 We are passionate about potatoes…and we’re even more passionate about our People! McCain knows the importance that food plays in people's lives – the power it has to bring people, families and communities together....
