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, intern
  
• Omar Chehab, Postdoc
  
• Tom Huix, PhD, co-advised with Eric Moulines and Alain Durmus
  
• Christophe Vauthier, PhD, co-advised with Quentin Mérigot
  
• Adrien Vacher, Postdoc at Inria co-advised by Flavien Léger
  

News

• February 2024: New preprint with Imad Aouali, Victor-Emmanuel Brunel, David Rohde; on Off Policy Learning and Evaluation in a Bayesian Framework using structured and informative priors.
  
  
• February 2024: New preprint with Pierre Marion, Peter Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet; on bilevel sampling.
  
  
• October 2023: New preprint with Francesca Crucinio and Nicolas Chopin; on the connection between mirror descent/optimization on measures and tempering schemes.
  
  
• September 2023: CAPSTONE projects (Master Data Science of Polytechnique) - projects between industrial mentors and Masters students. Reach out (before end of Sep !) if you are an industrial and interested in mentoring a Data Science project for 2024 edition happening in few months.
  
  
• September 2023: Co-organizing a workshop on Optimal Transport and Machine Learning at NeurIPS 2023, deadline 29th of September, consider submitting your work !
  
  
• July 2023: Imad Aouali will present our recent paper on Off-Policy Learning and Evaluation at ICML 2023 for an oral presentation.
  
  
• May 2023: co-organizing with Adil Salim and Avetik Karagulyan a minisymposium on Wasserstein gradient flows and their applications at SIAM OP 23.
  
  
• January 2023: Our paper with Lingxiao Li, Qiang Liu, Mikhail Yurochkin, and Justin Solomon on Sampling by optimizing a mollified (Riesz) interaction energy was accepted at ICLR 2023.


• September 2022: Our paper with Pierre-Cyril Aubin-Frankwoski and Flavien Léger on mirror descent on measure spaces, with applications to Sinkhorn for OT and EM, has been accepted to Neurips 2022.


• July 2022: Adil Salim and myself have presented a tutorial at ICML 2022 on Sampling with Wasserstein gradient flows. See here for the slides and here for the video (no ICML account needed).


• July 2022: New paper accepted at ICML with Lantian Xu and Dejan Slepcev, on the quantization of interacting particle systems (e.g. Stein Variational Gradient Descent, Maximum Mean Discrepancy or Kernel Stein Discrepancy Descent). Presenting it at the Monte Carlo and Sampling Session Tuesday 19th of July (6.30 pm poster session).

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].