Marc-H Lambert
About me
After a MSc in machine learning (MVA), I started a PhD in September 2020 under the supervision of Francis Bach and Silvère Bonnabel. I work on the interface between machine learning and robotics using variational inference to build new algorithms for online learning, kalman filtering and stochastic control. I also work part-time as a research engineer on smart sensors (infrared camera and radar).
Research
We propose new algorithms to solve nonlinear Bayesian estimation problems based on the variational approximation of an arbitrary distribution with a Gaussian or a mixture of Gaussians.
My research interests include:
Publications
Variational Dynamic Programming for Stochastic Optimal Control. M. Lambert, S. Bonnabel and F. Bach 2024 [https://arxiv.org/abs/2404.14806]
Low-rank plus diagonal approximations for Riccati-like matrix differential equations. S. Bonnabel, M. Lambert and F. Bach 2024 Journal on Matrix Analysis and Applications (SIMAX). [https://inria.hal.science/hal-04621158v1/document]
Variational Gaussian Approximation of the Kushner Optimal Filter. M. Lambert, S. Bonnabel and F. Bach 2023 International Conference on Geometric Science of Information, 395-404 [https://arxiv.org/pdf/2310.01859.pdf]
Variational inference via Wasserstein gradient flows. M. Lambert, S. Chewi, F. Bach, S. Bonnabel and P Rigollet 2022 Advances in Neural Information Processing Systems [https://arxiv.org/abs/2205.15902]
The continuous-discrete variational Kalman filter (CD-VKF). M. Lambert, S. Bonnabel and F. Bach 2022 IEEE 61st Conference on Decision and Control (CDC), 6632-6639 [https://inria.hal.science/hal-03665666v2/document]
The limited-memory recursive variational Gaussian approximation (L-RVGA). M. Lambert, S. Bonnabel and F. Bach 2023 Statistics and Computing 33 (3), 70 [https://arxiv.org/pdf/2303.14195.pdf]
The recursive variational Gaussian approximation (R-VGA). M. Lambert, S. Bonnabel and F. Bach 2021 Statistics and Computing 32 (1), 10 [https://inria.hal.science/hal-03086627/file/RVGA-HAL-v2.pdf]
Reviewer for:
Code
The algorithms associated to these articles are available here: [https://github.com/marc-h-lambert]
|