Avatar

Pierre-Cyril Aubin-Frankowski

PhD Student in Machine learning

MINES ParisTech, ENPC

Biography

Since September 2018, I am a Ph.D. student at the CAS laboratory at Mines ParisTech, advised by Nicolas Petit, working on learning the dynamics of control systems through kernel methods.

Lately, I have focused on dealing with the constraints appearing in optimal control or trajectory reconstruction. This is part of a work on general shape constraints in kernel regression with Zoltán Szabó, for e.g. non-crossing quantile regression.

I graduated from École polytechnique (X2013) in 2017, then obtained my Master degree (MVA, Mathematics-Vision-Learning) with Highest Honours after an internship with Jean-Philippe Vert (CBIO-Google) on gene network inference (based on single-cell RNA sequencing).

My PhD and my lyricomania do not leave me so much time to spare, but I occasionnaly paint.

Contact: pierre-cyril[dot]aubin(at)mines-paristech[dot]fr

Interests

  • Kernel Methods
  • Control Theory
  • Shape constraints

Education

  • PhD in Machine Learning, 2018-

    MINES ParisTech

  • MS (M2) in Machine Learning, 2016-2017

    ENS Paris-Saclay

  • MS (M1) in Applied Maths, 2013-2016

    École polytechnique

Recent & Upcoming

-Gave a talk at Séminaire de mathématiques appliquées du CERMICS at ENPC (Marne-la-Vallée) and Séminaire DEVI at ENAC (Toulouse), October 20, slides

-Presented a poster at SPIGL'20, information geometry summer school (Les Houches), July 20, poster

-Presented a poster at virtual MLSS 2020 Tübingen, machine learning summer school, July 20, slides

-Gave a talk at virtual IFAC World Congress, July 20, slides, video

-Gave a talk at virtual European Control Conference, May 20, slides, video

Publications

(Under revision) PCAF, Linearly-constrained Linear Quadratic Regulator from the viewpoint of kernel methods, June 2020, HAL, pdf

PCAF and Zoltan Szabo, Hard Shape-Constrained Kernel Machines, NeurIPS 2020, December 2020, [article], arXiv, HAL, pdf

PCAF, Nicolas Petit and Zoltan Szabo, Kernel Regression for Trajectory Reconstruction of Vehicles under Speed and Inter-Vehicular Distance Constraints, Proceedings IFAC WC 2020, July 2020, [article], pdf, slides, video

PCAF and Jean-Philippe Vert, Gene regulation inference from single-cell RNA-seq data with linear differential equations and velocity inference, Bioinformatics, June 2020, article, biorXiv, pdf, supp

PCAF and Nicolas Petit, Data-driven approximation of differential inclusions and application to detection of transportation modes, Proceedings ECC 2020, May 2020, [article], pdf, slides, video

PCAF, Lipschitz regularity of the minimum time function of differential inclusions with state constraints, Systems & Control Letters, May 2020, article, pdf

Experience

 
 
 
 
 

PhD student

MINES ParisTech

Sep 2018 – Present Paris
 
 
 
 
 

Public consultant/Graduate student

AgroParisTech and ENPC

Sep 2017 – Sep 2018 Paris

Hired as top civil servant (Corps des IPEF). Specialized in:

  • Banking and macroeconomics
  • General and Labour law
  • Environmental dialogue

Worked on artificial intelligence tailored to the strategies of the technical and scientific network of the French Ministry of Environment. I handed a report shortly after the Villani mission “For a meaningful Artificial Intelligence”. This report focuses on conceptualizing machine learning approaches and details its possible effects in institutions transforming due to the Digital Revolution.

 
 
 
 
 

Graduate student

École Normale Supérieure Paris-Saclay

Sep 2016 – Sep 2017 Cachan
Diploma obtained with Highest Honours. Specialized in:

  • General Machine Learning
  • Convex optimization
  • Kernel methods
 
 
 
 
 

Graduate student

École polytechnique

Sep 2016 – Sep 2017 Palaiseau
Diploma obtained with Highest Honours. Specialized in:

  • Applied Mathematics
  • Quantum Physics
  • (Neuro)biology