MACHINE LEARNING GROUP

TECHNISCHE UNIVERSITÄT KAISERSLAUTERN

Antoine Ledent

Post Doc

Bio

Antoine Ledent is a postdoctoral researcher at the department of computer science at TU Kaiserslautern in Prof. Dr. Marius Kloft's research group. He holds a Bachelor's and a Masters' degrees in mathematics from Clare College, University of Cambridge. Previously, he worked on low dimensional projections of high dimensional stochastic differential equations at the university of Luxembourg, where he obtained his PhD in 2017. He has served as a reviewer/PC member for AiStats, Neural Networks, NeurIPS, ECML and AAAI, and was in the top 10 percent of reviewers at NeurIPS 2020.

Research interests

Antoine Ledent is primarily working on statistical learning theory applied to neural networks, as well as matrix completion problems. Other interests include in stability analysis, multi-view problems, and interpretability.

Appointments and scientific matters
ledent@cs.uni-kl.de

Curriculum Vitae

Education

2017
PhD in Stochastic analysis from the University of Luxembourg
2013
Bachelors and Masters in Mathematics (BA+MMath) from the University of Cambridge (Clare College)

Professional Experience

since 2018
Postdoctoral Researcher at TU Kaiserslautern, computer science department
2013-2017
PhD Student under the supervision of Anton Thalmaier at the University of Luxembourg, mathematics department

Activities and honours

2018-2020
Top 10 percent of reviewers at NeurIPS 2020. Reviewer for AiStats, Neural Networks, NeurIPS, ECML and AAAI (2020 and 2021)
2007
First place (and only first prize) at the Belgian Mathematical Olympiad (years 5-6) + special prize as a 5th year student

Key publications and preprints

  • R. Alves*, A. Ledent*, R. Assunção, and M. Kloft. An Empirical Study of the Discreteness Prior in Low-Rank Matrix Completion. Proceedings of Machine Learning Research (PMLR): NeurIPS 2020 Workshop on the Pre-registration Experiment: An Alternative Publication Model For Machine Learning Research, (to appear) 2020.
  • Y. Lei*, A. Ledent*, and M. Kloft. Sharper Generalization Bounds for Pairwise Learning. Advances in Neural Information Processing Systems (NeurIPS) 33. (to appear) 2020.
  • Antoine Ledent*, Rodrigo Alves*, and Marius Kloft. Orthogonal Inductive Matrix Completion. Preprint, 2020.
  • Antoine Ledent, Waleed Mustafa, Yunwen Lei, and Marius Kloft. Norm-based generalisation bounds for convolutional neural networks. Preprint, 2019.
  • Antoine Ledent, Yunwen Lei, and Marius Kloft Improved Generalisation Bounds for Deep Learning Through $L^\infty$ Covering Numbers. NeurIPS Workshop on Machine Learning with Guarantees, 2019.
  • Antoine Ledent, Kusuoka-Stroock type bounds for densities related to low dimensional projections of high dimensional stochastic differential equations. PhD Thesis, 2017.
(* denotes equal contribution)