The research topics described in this Ph.D. thesis lie at the intersection of Machine Learning (ML) and Mathematical Programming (MP). The main contributions concern the Algorithm Configuration Problem (ACP) and the Distance Geometry Problem (DGP).In the first part of the manuscript, we provide introductions to MP and ML.In the second part, we survey the literature on the ACP. Given a configurable algorithm A and an input P for A, the ACP addresses the issue of identifying the parameter configuration c* of A ensuring the best algorithmic performance p in solving P. The ACP can be formulated as an optimization problem, where the constraints define the set of feasible configurations, and the objective optimizes the performance function p. Sin...
De nombreux algorithmes en Apprentissage Automatique utilisent une notion de distance ou de similari...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
Les problèmes d'optimisation combinatoire faisant partie de la classe de problèmes NP-difficiles son...
The research topics described in this Ph.D. thesis lie at the intersection of Machine Learning (ML) ...
The research topics of this Ph.D. thesis lie at the intersection of Machine Learning (ML) and Mathem...
International audienceWe propose a methodology, based on machine learning and optimization, for sele...
One common way of describing the tasks addressable by machine learning is to break them down into th...
We propose a methodology, based on machine learning and optimization, for selecting a solver configu...
The complexity theory distinguishes between problems that are known to be solved in polynomial time ...
Multiphysics simulation couple several computation phases. When they are run in parallel on memory-d...
Machine learning problems are sometimes solved with inappropriate methods, leading to sub-optimal re...
This thesis presents our contributions toinference and learning of graph-based models in computervis...
In this thesis, we are interested in the resolution by dynamic programming of Multistage Stochastic ...
Les métaheuristiques sont une famille d'algorithmes stochastiques destinés à résoudre des problèmes ...
De nombreux algorithmes en Apprentissage Automatique utilisent une notion de distance ou de similari...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
Les problèmes d'optimisation combinatoire faisant partie de la classe de problèmes NP-difficiles son...
The research topics described in this Ph.D. thesis lie at the intersection of Machine Learning (ML) ...
The research topics of this Ph.D. thesis lie at the intersection of Machine Learning (ML) and Mathem...
International audienceWe propose a methodology, based on machine learning and optimization, for sele...
One common way of describing the tasks addressable by machine learning is to break them down into th...
We propose a methodology, based on machine learning and optimization, for selecting a solver configu...
The complexity theory distinguishes between problems that are known to be solved in polynomial time ...
Multiphysics simulation couple several computation phases. When they are run in parallel on memory-d...
Machine learning problems are sometimes solved with inappropriate methods, leading to sub-optimal re...
This thesis presents our contributions toinference and learning of graph-based models in computervis...
In this thesis, we are interested in the resolution by dynamic programming of Multistage Stochastic ...
Les métaheuristiques sont une famille d'algorithmes stochastiques destinés à résoudre des problèmes ...
De nombreux algorithmes en Apprentissage Automatique utilisent une notion de distance ou de similari...
This thesis explores the use of discriminatively trained deformable contour models (DCMs) for shape-...
Les problèmes d'optimisation combinatoire faisant partie de la classe de problèmes NP-difficiles son...