Jump to content

Éric Moulines

From Wikipedia, the free encyclopedia
Eric Moulines in April 2019

Éric Moulines (born in Bordeaux on 24 January 1963) is a French researcher in statistical learning and signal processing.  He received the silver medal from the CNRS in 2010,[1] the France Télécom prize awarded in collaboration with the French Academy of Sciences in 2011. He was appointed a Fellow of the European Association for Signal Processing in 2012 and of the Institute of Mathematical Statistics in 2016.[2] He is General Engineer of the Corps des Mines (X81).

Biography

[edit]

Éric Moulines entered the École polytechnique in 1981, then went to study at Télécom ParisTech.

He began his career at the Centre national d'études des télécommunications where he worked on speech synthesis from text. He is involved in the development of new waveform synthesis methods called PSOLA (pitch synchronous overlap and add).[3]

After defending his thesis in 1990,[4] he joined the École Nationale Supérieure des Télécommunications as a lecturer. He then became interested in different problems of statistical signal processing. In particular, it contributes to the development of subspaces methods for the identification of multivariate linear systems[5] and source separation[6] and develops new algorithms for adaptive system estimation.

He received the authorization to direct research in 2006 and became a professor at Télécom Paris. He then devoted himself mainly to the application of Bayesian methods with applications in signal processing and statistics.[7]

Éric Moulines directed 21 theses, was president of the jury for 9 theses, was rapporteur for 10 theses, was member of the jury for 6 theses.[8]

Scientific work[9]

[edit]

He is interested in the inference of latent variable models[10] and in particular hidden Markov chains,[11][12] and non-linear state models (non-linear filtering)[13][14] In particular, it contributes to filtering methods using interacting particle systems.[13][14] He was more generally interested in the inference of partially observed Markovian models, coupling estimation and simulation problems with Monte Carlo Markov Chain Methods (MCMC). He has also developed numerous theoretical tools for the convergence analysis of MCMC algorithms, obtaining fundamental results on the long time behaviour of Markov chains.[15][16][17]

Since 2005, he has been working on statistical learning problems, including the analysis of stochastic optimization algorithms.[18][19]

He joined the Centre de mathématiques appliquées de l'École polytechnique[20] as a professor in 2015. He is interested in Bayesian inference from large scale models, with applications in uncertainty quantification in statistical learning.

Honours and awards

[edit]

References

[edit]
  1. ^ "Médaille d'argent 2010 : Éric Moulines" (PDF). cnrs.fr.
  2. ^ "Faculty of Computer Science / International Laboratory of Stochastic Algorithms and High-Dimensional Inference".
  3. ^ Eric Moulines, Francis Charpentier, « Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones », Speech Communication, 1990, pp. 453–467
  4. ^ "Biographie".
  5. ^ E Moulines, P Duhamel, JF Cardoso, S Mayrargue, « Subspace methods for the blind identification of multichannel FIR filters », IEEE Transactions on signal processing,, 1995, pp. 516–525
  6. ^ Belouchrani, Adel and Abed-Meraim, Karim and Cardoso, J-F and Moulines, Eric, « A blind source separation technique using second-order statistics », IEEE Transactions on signal processing, 1997, pp. 434–444
  7. ^ "Apprentissage Bayésien". YouTube.
  8. ^ "Thèses".
  9. ^ "Research gate".
  10. ^ O Cappé, E Moulines, « On‐line expectation–maximization algorithm for latent data models », Journal of the Royal Statistical Society, Series B (Statistical Methodology), 2009, pp. 593–613
  11. ^ R Douc, E Moulines, T Rydén, « Asymptotic properties of the maximum likelihood estimator in autoregressive models with Markov regime », The Annals of statistics, 2004, pp. 2254–2304
  12. ^ O. Cappé, E. Moulines, T. Ryden, « Inference in Hidden Markov Models », Springer Series in Statistics, 2006
  13. ^ a b R Douc, A Garivier, E Moulines, J Olsson, « Sequential Monte Carlo smoothing for general state space hidden Markov models », The Annals of Applied Probability, 2011, pp. 2109–2145
  14. ^ a b R Douc, E Moulines, D Stoffer, « Nonlinear time series: Theory, methods and applications with R examples », Chapman and Hall/CRC, 2014
  15. ^ C Andrieu, É Moulines, « On the ergodicity properties of some adaptive MCMC algorithms », The Annals of Applied Probability, 2006, pp. 1462–1505
  16. ^ R Douc, E Moulines, P Priouret, P Soulier, « Markov Chains », Springer, 2018
  17. ^ A Durmus, E Moulines, « Nonasymptotic convergence analysis for the unadjusted Langevin algorithm », The Annals of Applied Probability, 2017, pp. 1551–1587
  18. ^ A Garivier, E Moulines, « On upper-confidence bound policies for switching bandit problems », International Conference on Algorithmic Learning, 2011, pp. 174–188
  19. ^ E Moulines, FR Bach, « Non-asymptotic analysis of stochastic approximation algorithms for machine learning », Advances in Neural Information Processing Systems, 2011, pp. 451–459
  20. ^ Nouvelle, L'Usine (7 February 2018). "Le statisticien historique : Éric Moulines, professeur à l'École polytechnique". usinenouvelle.com.