Dear all,
Apologies for cross-posting.
We have multiple openings for Interns, PhD students, and Postdoctoral Researchers at the SIERRA Machine Learning Team (Paris, France) which is a joint laboratory between INRIA, the CS Dept. at Ecole Normale Superieure, and CNRS.
Subject:All the positions will be a part of the ERC Starting Grant (2021) – DYNASTY (Dynamics-Aware Theory of Deep Learning) project, which focuses on various aspects of Deep Learning Theory. The potential topics include (and are not limited to):- Generalization bounds for neural networks- Implicit regularization- Non-convex optimization- Network compression
Candidate Profile:
– For the Internship positions: Enrollment at a masters/PhD program is required, preferably pure/applied mathematics or statistics. – For the Phd positions: A masters degree in applied mathematics, statistics, or computer science is required. (A direct PhD after undergrad is not possible).- For the Postdoc positions: PhD degree (and publications) in ML Theory or related fields such as applied mathematics (preferably applied probability, stochastic analysis, operations research), statistics, computer science.
A background on dynamical systems / fractal geometry / heavy-tailed stochastic recursions will be a plus.
I will not consider candidates that only have an applications background.
The SIERRA Team:
The researcher will be hosted at the INRIA Paris center, in downtown Paris.
A non-exhaustive list of topics that are currently investigated by the researchers of the SIERRA team includes:
– Large scale non-smooth optimization methods.
– Distributed optimization methods (asynchronous stochastic gradient optimization).
– First order-methods.
– Nonconvex optimization.- Kernel methods.
Application Process / Deadline:
– There is no specific deadline. The applications will be considered on a “first-come-first-serve” basis. – Internships typically take 3-6 months. The timing can be flexible. – In the application, please send a resume, a motivation letter, and at least one reference letter to Umut Simsekli — “umut.simsekli at inria.fr“.
Best regards,Umut Simsekli–https://www.di.ens.fr/~simsekli/