Post-Doctoral Research Visit F/M Post-doctoral Researcher - Expressivity of Implicit neural networks for data-driven stability and safety certificates
Contract type : Fixed-term contract
Level of qualifications required : PhD or equivalent
Fonction : Post-Doctoral Research Visit
Level of experience : Up to 3 years
About the research centre or Inria department
The Inria Saclay-Île-de-France Research Centre was established in 2008. It has developed as part of the Saclay site in partnership with Paris-Saclay University and with the Institut Polytechnique de Paris .
The centre has 41 project teams , 27 of which operate jointly with Paris-Saclay University and the Institut Polytechnique de Paris; Its activities occupy over 600 people, scientists and research and innovation support staff, including 44 different nationalities.
Context
This postdoctoral position is in partnership between Inria Saclay, team DISCO, and the Department of Computer Science, University College London, within the UCL-Inria Joint Centre.
The goal of the collaboration is to develop novel methods for computing safety and stability certificates based on neural network parameterizations of Lyapunov functions. Particular attention will be given to analyzing the expressivity of these models as a function of their parameters, including the transition between smooth and non-smooth activation functions. The project will also investigate and compare the expressivity of feedforward and implicit neural networks under equivalent parameterization constraints. In addition, methodological advances will be pursued to improve the training of implicit neural networks.
International collaboration
The job position requires the applicant to spend 12 months in the Inria Saclay, France, and 12 months in London, with a calendar to be defined.
Assignment
Mission:
Under the supervision of Prof. Giorgio Valmorbida and Prof. Akin Delibasi, the postdoctoral researcher will be responsible for developing the research program outlined in the research proposal.
The research proposal is available for download in:
https://filesender.renater.fr/?s=download&token=529793d9-630b-4a96-86c2-478a2ad2bf48
Responsibilities:
The postdoctoral researcher will organize weekly meetings, write monthly progress reports, and give a broader team presentation every 6 months. As part of a team the researcher will help organise the scientific discussions of the team and, if funding is available, co-supervise MSc students.
Main activities
Main activities:
- Develop a study on the expressivity of implicit Neural Networks,
- propose a curriculum learning strategy to transition from smooth activation functions to non-smooth activation functions,
- compute Lyapunov function based on an implicit NN to assess
- stability and safety,
- compute control laws based on data-driven control Lyapunov functions.
Among other activities, the research will
- Develop NN training strategies for implicit NN.
- Write documentation of developed software
- Report progress
- Organize project meetings
- Publish the results in the journals and conferences of Automatic Control and Machine Learning
- Communicate the results within the group
Skills
Skills: Advanced programming proficiency in Python and MATLAB.
Languages: Fluency in English is required; proficiency in French is considered an asset.
Interpersonal Skills: The candidate will be evaluated on their ability to interact effectively with colleagues and collaborate within an international team. Demonstrated communication skills, including the ability to engage with a broader audience, will be highly valued.
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
Remuneration
€2,788 gross per month
General Information
- Theme/Domain :
Optimization and control of dynamic systems
Scientific computing (BAP E) - Town/city : Palaiseau
- Inria Center : Centre Inria de Saclay
- Starting date : 2026-11-02
- Duration of contract : 2 years
- Deadline to apply : 2026-10-01
Warning : you must enter your e-mail address in order to save your application to Inria. Applications must be submitted online on the Inria website. Processing of applications sent from other channels is not guaranteed.
Instruction to apply
Defence Security :
This position is likely to be situated in a restricted area (ZRR), as defined in Decree No. 2011-1425 relating to the protection of national scientific and technical potential (PPST).Authorisation to enter an area is granted by the director of the unit, following a favourable Ministerial decision, as defined in the decree of 3 July 2012 relating to the PPST. An unfavourable Ministerial decision in respect of a position situated in a ZRR would result in the cancellation of the appointment.
Recruitment Policy :
As part of its diversity policy, all Inria positions are accessible to people with disabilities.
Contacts
- Inria Team : DISCO (DRI)
-
Recruiter :
Valmorbida Giorgio / giorgio.valmorbida@inria.fr
The keys to success
We seek a postdoctoral researcher to contribute to research at the interface of artificial intelligence and control systems within a dynamic, internationally oriented scientific environment. The successful candidate is expected to demonstrate strong intellectual curiosity, a high capacity for autonomous learning, and the ability to engage effectively in collaborative research.
The candidate must possess recognized expertise in artificial intelligence methods (including machine learning, reinforcement learning, and data-driven modeling) and in nonlinear control systems. A solid theoretical background is required, particularly in Lyapunov stability analysis and optimization-based control design. Strong programming skills are expected. The research will primarily focus on the mathematical analysis of implicit neural network models, with an emphasis on their expressivity for deriving stability certificates and synthesizing control laws.
Applicants must hold a PhD in control theory, artificial intelligence, or a closely related discipline. A significant publication record in leading international journals and conferences is required. The quality of the applicant’s publications will be assessed on the basis of originality, scientific innovation, mathematical rigor, and clarity of presentation.
About Inria
Inria is the French national research institute dedicated to digital science and technology. It employs 2,600 people. Its 200 agile project teams, generally run jointly with academic partners, include more than 3,500 scientists and engineers working to meet the challenges of digital technology, often at the interface with other disciplines. The Institute also employs numerous talents in over forty different professions. 900 research support staff contribute to the preparation and development of scientific and entrepreneurial projects that have a worldwide impact.