Postdoc position Foundations of resource-efficient large-scale learning

Context
Within the framework of a partnership
Founded in 1880, the Ecole Normale Supérieure de Lyon (www.ens-lyon.fr) is one the most prestigious “Grand Écoles” in France with students selected from the top 5% among all students in the country and among the best students from abroad. The mission of the university is training national and international future professors, researchers, senior civil servants as well as business and political leaders, and to advance research in several disciplines ranging from humanity to natural sciences.
Established in 1967, Inria (www.inria.fr) is the only public research body in France fully dedicated to computational sciences. Combining computer sciences with mathematics, Inria’s 3,500 researchers strive to invent the digital technologies of the future. Educated at leading international universities, they creatively integrate basic research with applied research and dedicate themselves to solving real problems, collaborating with the main players in public and private research in France and abroad and transferring the fruits of their work to innovative companies.
Assignment
Solid algorithmic and mathematical foundations are essential to endow machine learning systems with guaranteed utility, resource-efficiency and trustworthiness. A particular challenge is to control the tradeoffs between performance and computational footprint to exploit massive data streams.
The recruited postdoc will conduct a vigorous research program within the scope of the project, and is expected to show independence and team working attitude at the same time.
The successful candidate, which can come from different areas (applied mathematics and statistics, signal processing, machine learning, information theory, computer science) is expected to bring expertise to the AllegroAssai task force and will be encouraged to develop collaborations with other groups at ENS de Lyon.
The position is endowed with travel, computing, and experimental resources.
Sample research topics include:
Expressivity and Robustness of Sparse Deep Networks; Provable Algorithms for Sparse Deep Learning; Random Sketches for Efficient Manifold & Graph-based Learning
.
Main activities
Sample research topics include:
Expressivity and Robustness of Sparse Deep Networks; Provable Algorithms for Sparse Deep Learning; Random Sketches for Efficient Manifold & Graph-based Learning
.
Skills
Candidates should hold a Ph.D., and will either be applied mathematicians with interest for statistical signal processing, and good programming skills, or originate from signal processing / computer science with solid background in applied mathematics and statistics. Previous experience in sparse signal representations or statistical machine learning is preferred, but experience in related areas is suitable.