Pierre Laforgue

alt text 

Quantitative Researcher
Capital Fund Management

Contact
Email: pierre [dot] laforgue1 [at] gmail [dot] com
Others: Google Scholar, GitHub, LinkedIn

About me

I am currently a quantitative researcher at Capital Fund Management.

Prior to this, I was a postdoctoral researcher at the University of Milan, Italy. I worked among the LAILA team led by professor Nicolò Cesa-Bianchi.
My recent research interests revolve around multitask online learning and bandit algorithms, with applications to federated learning.

I also co-supervised two PhD theses:

  • Giulia Clerici, worked on nonstationary bandits for music recommendation (co-supervised with N. Cesa-Bianchi)

  • Tamim El Ahmad, studied sketching algorithms to scale-up operator-valued kernel machines (co-supervised with F. d'Alché-Buc)

I obtained my PhD from Télécom Paris, under the supervision of professors Florence d'Alché-Buc and Stephan Clémençon.
You can find more about my background on my LinkedIn or in my resume.

Research Interests

My research interests revolve around Learning Theory, and include more precisely:

  • Multitask Online Learning

  • Bandit Algorithms

  • Federated Learning and Privacy Preservation

  • Kernel Methods and Sketching Algorithms

  • Robust Learning and Median-of-Means

  • Statistical Learning and Sample Bias Issues

My list of publications is available here.

News

  • Jun. 24: our paper on linear bandits with memory got accepted at TMLR (joint work with G. Clerici and N. Cesa-Bianchi) !

  • May 24: our paper on deep sketched output kernel regression got accepted at ECML (joint work with T. El Ahmad, J. Yang and F. d'Alché-Buc) !