CIMI Workshop on "Optimization and Learning"
Dates: september 10-13, 2018.
Location: Toulouse, France.
Information and registration: website
CIMI Workshop on "Optimization and Machine Learning"
The CIMI Workshop on « Optimization and Learning » take place at Institut de Mathématiques de Toulouse (IMT) and is part of the thematic semester « Optimization » organized by Labex CIMI.
The workshop will focus on important challenges in optimization for machine learning, pertaining to the following subtopics:
- Representation learning. Artificial intelligence, signal & image processing and automatic language processing, among other disciplines, motivate the development of novel methodology for matrix factorization, dictionary learning and deep learning: the workshop will present recent results on the characterization and obtention of the solutions to these non-convex problems.
- Stochastic optimization. In some problems pertaining to computational statistics, signal & image processing, risk computations or learning in large dimension, the objective function is intractable or available up to some approximations. The workshop will present methodological & theoretical advances to address such settings, in the context of non-smooth and non-convex optimization and including online and distributed algorithms.
- Optimization with uncertainty. The workshop will address the optimization of backbox functions, possibly in the presence of noise, by means of Gaussian Processes (GP) or bandit models. It will include a mini-course on the use of GPs for optimization, and a series of presentations on recent advances in multi-armed bandit models and GP-based procedures, with a focus on theoretical guarantees and in particular bounds on the cumulated regret.
The workshop will include three mini-courses (3 x 3h) and a dozen one hour talks. Participants are also invited to present their work during a poster session (see the registration form for the application).
Confirmed speakers for the mini-courses (3 courses of 3h each)
- Andreas Krause (Leaning and Adaptive Systems group, ETH Zurich; Switzerland)
- Georges Lan (Georgia Institute of Technologia, Atlanta; USA)
- René Vidal (Johns Hopkins University, USA)
Confirmed speakers for the one hour talks
- Francis Bach (DI ENS, Centre de recherche INRIA PARIS; France)
- Gérard Biau (LPSM, Sorbonne Université, Paris; France)
- Richard Combes (Laboratoire des signaux et systèmes, Supelec; Gif sur Yvette; France)
- Camille Couprie (Facebook; France)
- Nicolas Gillis (Université de Mons; Belgium)
- Jose Miguel Hernandez-Lobato (Dpt of Engineering, University of Cambridge; UK)
- Anatoli Juditsky (Laboratoire J. Kuntzmann, Université Grenoble Alpes, France)
- Jason Lee (Data Sciences and Operations Dpt, Univ. Southern California; USA)
- Eric Moulines (CMAP, Ecole Polytechnique, Orsay; France)
- Ohad Shamir (Dpt Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot; Israël)
- Michal Valko (SequeL team, INRIA Lille - Nord Europe; Lille; France)
- Lenka Zdeborova (Institut de Physique Théorique, CEA Saclay; Paris; France)
François Bachoc, Cédric Févotte, Gersende Fort and Sébastien Gadat
Nicolas Dobigeon, Aurélien Garivier, François Malgouyres, Edouard Pauwels, Laurent Risser and Aude Rondepierre