Kamélia Daudel

About me

I was a postdoctoral researcher in the Department of Statistics at the University of Oxford working with Arnaud Doucet.

I defended my PhD in 2021 at Télécom Paris and I was advised by Randal Douc, François Roueff and François Portier. My PhD thesis is available here and I received the first prize of IP Paris Best Thesis Award 2022 for it.

My current research lies in the field of Approximate Inference. In particular, I am interested in Variational Inference methods which go beyond the commonly-used parametric variational distribution framework and which involve flexible families of divergence measures (e.g. the $\alpha$-divergence family).

Email : kamelia [dot] daudel [at] gmail [dot] com


  •   Bayesian Statistics
  •   Monte Carlo Methods
  •   Optimisation
  •   Information Geometry


  • Télécom Paris (2018-2021)

    PhD in Applied Mathematics

  • University of Oxford (2017-2018)

    MSc in Mathematical and Computational Finance

  • Eurecom (2016-2017)

    Master's Degree in Communication System Security

  • Télécom Paris (2015-2018)

    Diplôme d’ingénieur


(2023). Monotonic Alpha-divergence Minimisation for Variational Inference. Journal of Machine Learning Research, 24(62):1–76.


(2021). Mixture weights optimisation for Alpha-Divergence Variational Inference. In Advances in Neural Information Processing Systems, volume 34, pages 4397–4408.


(2021). Infinite-dimensional gradient-based descent for alpha-divergence minimisation. Ann. Statist. 49 (4) 2250 - 2270.