PhD - "Optimization and generalization capacity of quantum machine learning algorithms" F/M
ref :2023-24165 | 07 Apr 2023
apply before : 31 Aug 2023
4 rue du clos Courtel 35510 CESSON SEVIGNE - France
about the role
In a context of malware detection, and in a desire to improve our artificial intelligence of our artificial intelligence algorithms, the PhD student will work on several aspects of quantum machine learning, aiming at optimizing existing algorithms.
Placing himself in a context of little data and few resources available on current quantum machines, the PhD student will have to become familiar with the tools of quantum machine learning, and understand the use of Fisher information matrices. Indeed, the information matrix is obtained from the quantum circuit used, and its rank is closely related to the dimension of the ambient Hilbert space and to the expressiveness of the circuit, i.e. the capacity to explore a more or less vast region of this space. We can quote in particular the works of D. Sutter and A. Abbas ([1], [2]) who relate the Fisher information matrix to the effective dimension of a model, which allows to measure the capacity and expressiveness of the model [8]. Better mastering our ability to explore the ambient Hilbert space from a quantum model allows us to optimize the learning of the model, and thus to succeed with less data to obtain satisfactory results.
The Fisher information matrices, and more particularly their rank, are also linked to the dimension of the Lie algebra generated from the quantum gates used by the quantum model. The PhD student will thus be led to study Lie theory and group representations, which are sources of information in order to choose the quantum models to be used according to certain particularities observed on the input data. This is based on the work of M. Cerezo [3][4][6][7] who studies in particular the symmetries present in the input data in order to propose quantum algorithms respecting these symmetries, called equivariants, and thus allowing a better learning, from less data.
The PhD student will also study notions of over-parametrization, which limit the number of parameters to be used in a quantum algorithm by a quantity depending on the dimension of the ambient Hilbert space or of its associated Lie algebra [5]. This ensures that our algorithms are deep enough to provide optimal performance, without the need to to add superfluous parameters.
Currently, quantum computers are still subject to sources of error such as the noise induced by each quantum operation. It crucial, for a use as soon as possible, to address these issues in order to reduce the number of operations necessary to obtain a satisfactory learning.
about you
Skills (scientific and technical) and personal qualities required by the position
- Very good mathematical and physical knowledge related to quantum mechanics and artificial intelligence (group theory, proba...)
- Knowledge in python and Qiskit
- Knowledge of malware or desire to discover the subject
Education required (master, engineering degree, PhD, scientific and technical field ...)
- Master's degree in pure or applied mathematics or in theoretical physics
Desired experiences (internships, …)
Master 2 research internship on a related topic (Quantum or Lie group theory)
additional information
This offer gives the PhD student the opportunity to mix several research fields (AI, physics and cybersecurity) to participate in a groundbreaking research topic. Quantum computing is becoming an increasingly important topic in recent years and cybersecurity is one of the highest priority topics of the moment due to the global context. Moreover, the PhD student will have the opportunity to work in a stimulating environment with many other researchers from different fields.
Attractive remuneration for this position.
Bibliography
D. Sutter and A. Abbas ([1], [2]) who relate the Fisher information matrix to the effective dimension of a model, which allows us to measure the capacity and expressiveness of the model [8]. Better mastering our ability to explore the ambient Hilbert space from a quantum model allows us to optimize its learning, and thus to succeed with less data to obtain satisfactory results more easily. The Fisher information matrices, and more particularly their rank, are also related to the dimension of the Lie algebra generated from the quantum gates used by the quantum model.
This is the case of M. Cerezo [3][4][6][7] who study in particular the symmetries present in the input data in order to propose quantum algorithms respecting these symmetries, called equivariants, and thus allowing a better learning, from less data.
department
Orange Innovation brings together the research and innovation activities and expertise of the Group's entities and countries. We work every day to ensure that Orange is recognized as an innovative operator by its customers and we create value for the Group and the Brand in each of our projects. With 720 researchers, thousands of marketers, developers, designers and data analysts, it is the expertise of our 6,000 employees that fuels this ambition every day.
Orange Innovation anticipates technological breakthroughs and supports the Group's countries and entities in making the best technological choices to meet the needs of our consumer and business customers.
In Orange Innovation, the doctorant will be integrated́ within the securitý teams of the IT infrastructure & Services - IT&S domain. The teams are responsible for maintaining a high level of expertise in securitý for the Orange Group combining research and applications for operational entities. They particularly focus on the case of cloud computing security, intrusion detection/protection, strong authentication, cryptography, cyber security and personal data protection (anonymization, traceability, ...). The team is based in Rennes-Cesson-Sévigné on the Orange Innovation "Atalante" site.
contract
Thesis
Only your skills matter
Regardless of your age, gender, origin, religion, sexual orientation, neuroatypia, disability or appearance, we encourage diversity within our teams because it is a strength for the collective and a vector of innovation. Orange Group is a disabled-friendly company: don't hesitate to tell us about your specific needs.
Similar offers
Orange SA
Orange Group
of our employees are proud to work for Orange
recommend Orange as a good place to work
is the candidate experience in France, in the category of companies with over 1,000 employees
Since 2011, Orange has GEEIS (Gender Equality European & International Standard) certification in some twenty countries