Accueil › Project › SDwithMI

SDwithMI

Convergence of Stochastic Descent Algorithms with Markovian Inputs

Project funded by the Labex CIMI

Topic: Convergence of Stochastic Descent-based algorithms with Markovian inputs for non-smooth and convex optimization :

  1. Convergence of perturbed iterative algorithms, for convex composite optimization
  2. Acceleration methods
  3. Design and Convergence of Penalized Stochastic Approximation EM algorithms
  4. Iterative algorithms for Quantile and Superquantile estimations.

P.I.: Gersende Fort

When: from January 2018 to December 2019

Local participants:

External favouref partners:

Scientific production:

Papers

  1. G. Fort, E. Ollier and A. Leclerc-Samson. Stochastic Proximal Gradient Algorithms for Penalized Mixed Models. Statistics and Computing, 29(2):231-253, 2019.
  2. G. Fort, L. Risser, Y. Atchadé and E. Moulines. Stochastic FISTA algorithms: so fast ? Proceedings of the IEEE Statistical Signal Processing workshop, pp.796-800, June 2018.
  3. S. Crepey, G. Fort, E. Gobet and U. Stazhynski. Quantification d’incertitude pour l’Approximation Stochastique. Accepté, Actes de conférence du GRETSI 2019.
  4. S. Crepey, G. Fort, E. Gobet and U. Stazhynski. Uncertainty quantification for Stochastic Approximation limits using Chaos Expansion. Accepted for publication in SIAM-ASA Journal on Uncertainty Quantification, 2020.
  5. C. Dossal – xxx
  6. C. Dossal – xxx
  7. L. Risser – xxx

Talks

  1. By G. Fort. Conference IEEE Statistical Signal Processing; Freiburg, Germany; June 2018.
  2. By C. Dossal. 1st Workshop « Advances in nonsmooth analysis and optimization », Erice, Italy; June 2019.
  3. By G. Fort. Conférence francophone GRETSI, Lille; Août 2019.
  4. By G. Fort. PGMO days, December 2019.
  5. By G. Fort. Conference « Optimization for Machine Learning », CIRM, Mars 2020.

Workshop

Co-organization of the semester « Optimization » funded by the Labex CIMI : a first workshop in June 2018 on « Aspects fondamentaux et Exploitation de la structure » with C. Dossal and S. Gadat as co-organizers ; and a second workshop on « Optimization and Learning » co-organized by G. Fort, S. Gadat, A. Garivier, L. Risser and C. Févotte.

Stage

  • M2  ( see C. Dossal)

And after ?

These CIMI fundings were a cornerstone for its members, in order to apply to other projects funded by national grants:

  • C. Dossal, G. Fort and S. Gadat are part of a project funded by the french National Research Agency (ANR), starting in Autumn 2019.  The P.I. is S. Gadat. It involves researchers from Bordeaux (IMB) and Toulouse (IMT, TSE-R).
  • G. Fort, S. Gadat and L. Risser are part of a project funded by the Fondation Simone and Cino Del Duca, starting in January 2020. The P.I. is G. Fort
  • S. Dobigeon, C. Févotte, and L. Risser are members of a national program for Artificial Intelligence, « Artificial and Natural Intelligence Toulouse Institute (ANITI) », starting in Autumn 2019.

 

Mentions Légales