Frank NIELSEN (PhD'96, Habilitation HDR 06)
My motto: "Invariance is the only constant in change"
Sony CSL, Fellow
 
@FrnkNlsn Blog
460+ research cards
ACM SM, IEEE SM, ELLIS F

Fields of interest:

• Geometric science of information
• Computational information geometry
  (poster on the genesis of information geometry)
• Computational geometry
• Theory of (dis)similarities (poster) and aggregators
  • A note on the Jensen-Shannon divergence
• Machine learning and artificial intelligence
• Computer vision
• Visual computing and computational photography
• Computational mathematics

Community: Journal editor/Event organizer

• The Many Faces of Information Geometry, AMS Notices (January 2022)
• Slides: Information Geometry: An Invitation for Machine Learning, NeurIPS Meetup Japan (14th December 2021)
• Slides: Bregman divergences,dual information geometry, and generalized comparative convexity
• More Slides and 📹 video
• Publications (and preprints [Journal and Letters] )
   
  
• Some introductory and overview papers:
  • Cramer-Rao lower bound and information geometry
    → A first read introducing the Fisher information matrix, the CRLB, and the differential-geometrization of statistics
  • An elementary introduction to information geometry
    → Learn what is the fundamental theorem of information geometry!
  • Introduction to Bregman manifolds
    → Learn the dually flat spaces of exponential families and mixture families, and the dual generalized Pythagorean theorems
  • What is... an information projection?
    → Projection along geodesics, projection as divergence minimization, cases where we have uniqueness of projections
  • Slides and video:
    • slides From geometric learning machines to the geometry of AI
    • slides Information geometry for information sciences: A first intuitive overview
    • video The dual geometry of Shannon information and its applications
  • Five selected publications:
    • Bregman Voronoi diagrams, Discrete and Computational Geometry, 2010.
    • The Burbea-Rao and Bhattacharyya centroids, IEEE Transactions on Information Theory, 2011.
    • An information-geometric characterization of Chernoff information, IEEE Signal Processing Letters, 2013.
    • On the chi square and higher-order chi distances for approximating f-divergences, IEEE Signal Processing Letters, 2013.
    • Generalized Bhattacharyya and Chernoff upper bounds on Bayes error using quasi-arithmetic means, Pattern Recognition Letters, 2014.
  • Five selected collaborative publications tackling various applications:
    • Imaging: Statistical region merging, IEEE Transactions on pattern analysis and machine intelligence, 2014.
    • Music: DeepBach: a Steerable Model for Bach Chorales Generation, ICML 2017.
    • Computer graphics: Volumetric illustration: designing 3D models with internal textures, SIGGRAPH, 2004.
    • Computer vision: Shape retrieval using hierarchical total Bregman soft clustering, IEEE transactions on pattern analysis and machine intelligence, 2012.
    • Telecommunications: Combinatorial optimization algorithms for radio network planning, Theoretical Computer Science 2001.
  • Some research cards
• Textbooks (AMZ book author web page):
  • Introduction to HPC with MPI for Data Science, Springer, 2016. (also translated in Chinese)
    Sample chapter 7:Partition-based clustering with k-means
  • A Concise and Practical Introduction to Programming Algorithms in Java, Springer, 2009. (also translated in Chinese)
  • Visual Computing: Geometry, Graphics, and Vision, Charles River Media, 2005.