ANTOINE GAUTIER
Researcher/Ph.D. Student,
Faculty of Mathematics and Computer Science,
Saarland University
Address:
Saarland University
Saarland Informatics Campus
Building E 1 1, Room 228
66123 Saarbrücken
Germany
phone: +49 681 302-57331
antoine(dot)gautier(at)uni-saarland(dot)de
ABOUT ME
I obtained my first degree in mathematics at EPFL (Lausanne, Switzerland) during which I had the chance to study one year in Berlin. Then I did my master (also at EPFL) in the chair of Numerical Algorithm and High-Performance Computing. I'm basically interested in all kind of mathematics and especially in spectral theory and numerical analysis. My research concern numerical algorithm for solving non-linear eigenvalue problems.
PUBLICATIONS
- A. Gautier, F. Tudisco and M.Hein
The Perron-Frobenius Theorem for Multi-homogeneous Maps
preprint, available at arxiv - A. Gautier, Q. Nguyen and M. Hein
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
NIPS 2016. PDF
Supplement: PDF (code will be available soon) - Q. Nguyen, A. Gautier and M. Hein
Nonlinear Spectral Methods for Nonconvex Optimization with Global Optimality
NIPS'16 Workshop On Optimization for Machine Learning. PDF - A. Gautier and M. Hein
Tensor norm and maximal singular vectors of non-negative tensors - a Perron-Frobenius theorem, a Collatz-Wielandt characterization and a generalized power method
preprint, available at arxiv. (project page)
- Q. Nguyen, F. Tudisco, A. Gautier and M. Hein
An Efficient Multilinear Optimization Framework for Hypergraph Matching
arXiv:1511.02667v1 Link - Q. Nguyen, A. Gautier and M. Hein
A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching
CVPR 2015 (oral presentation). PDF (Supplementary material: PDF )
( project page)