Anna Korba

About me

Since September 2020, I am an assistant professor at ENSAE/ CREST in the Statistics Department.

My main line of research is machine learning. I have been working on kernel methods, optimal transport, optimisation, particle systems and preference learning. At the moment I am particularly interested in sampling and optimisation methods.

I am also a co-administrator of the Master Data Science of Ecole Polytechnique.

Team

With my academic activities, I am lucky to work closely with the following people:

• Imad Aouali, PhD, co-advised with Victor-Emmanuel Brunel and David Rohde
  
• Clément Bonet, Postdoc
  
• Clémentine Chazal, PhD
  
• Omar Chehab, Postdoc
  
• Marguerite Petit-Talamon, Intern
  
• Christophe Vauthier, PhD, co-advised with Quentin Mérigot
  
• Adrien Vacher, Postdoc co-advised with Flavien Léger
  

Alumni

• Tom Huix, PhD (2021-2024), co-advised with Eric Moulines and Alain Durmus.
  

News

• October 2024: Gave a talk at Yale at a workshop on sampling, and MIT
  
  
• October 2024: Tom Huix brillantly defended his PhD, congrats!!
  
  
• July 2024:
  • 2 papers accepted at ICML 2024; the first on tempering with my colleagues Nicolas Chopin and Francesca Crucinio; the second on variational inference with mixtures of Gaussians with Tom Huix, Alain Durmus, Eric Moulines.
  • 2 (workshop) papers accepted at ICML 2024 (on Diffusion models); (1) implicit diffusion paper at the "Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators" with Pierre Marion, Peter Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet, about optimizing reward functions while learning diffusion models; (2) a paper on a practical diffusion path for sampling at the "Workshop on Structured Probabilistic Inference & Generative Modeling" with Omar Chehab using a dilation path to adapt Diffusion models to the Bayesian inference setting.
  
  
• July 2024: 1 paper accepted at UAI 2024, on regularized importance-weighted estimators for off-policy learning and evaluation, with Imad Aouali, Victor-Emmanuel Brunel, David Rohde.
  
  
• June 2024: New preprint with Clément Bonet, Théo Uscidda, Adam David, Pierre-Cyril Aubin-Frankowski, on adapting Mirror Descent and Preconditioned Gradient schemes to the Wasserstein spaces. Applications to sampling and learning single-cell perturbation responses.
  
  
• February 2024: New preprint with Imad Aouali, Victor-Emmanuel Brunel, David Rohde; on off-policy learning and evaluation in a Bayesian framework using structured priors.
  
  

Bio

From December 2018 to August 2020 I was a postdoctoral researcher at Gatsby Unit, University College London (UCL), working with Arthur Gretton.
From October 2015 to October 2018, I was a PhD student at Télécom ParisTech, in the S2A (Signal, Statistics and Learning) team, supervised by Stephan Clémençon .
Before that in 2015, I graduated the Master MVA (Machine Learning and Computer Vision) from ENS Cachan and ENSAE.

More details can be found in my resume [EN].