no code implementations • 8 May 2024 • Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Michèle Sébag, Marc Schoenauer
This paper provides a comprehensive review of deep structural causal models (DSCMs), particularly focusing on their ability to answer counterfactual queries using observational data within known causal structures.
no code implementations • 3 Mar 2024 • Mouadh Yagoubi, Milad Leyli-Abadi, David Danan, Jean-Patrick Brunet, Jocelyn Ahmed Mazari, Florent Bonnet, Asma Farjallah, Marc Schoenauer, Patrick Gallinari
The aim of this competition is to encourage the development of new ML techniques to solve physical problems using a unified evaluation framework proposed recently, called Learning Industrial Physical Simulations (LIPS).
no code implementations • 13 Feb 2024 • Matthieu Nastorg, Jean-Marc Gratien, Thibault Faney, Michele Alessandro Bucci, Guillaume Charpiat, Marc Schoenauer
The proposed GNN-based preconditioner is used to enhance the efficiency of a Krylov method, resulting in a hybrid solver that can converge with any desired level of accuracy.
no code implementations • 11 Sep 2023 • Emmanuel Menier, Sebastian Kaltenbach, Mouadh Yagoubi, Marc Schoenauer, Petros Koumoutsakos
In recent years, techniques based on deep recurrent neural networks have produced promising results for the modeling and simulation of complex spatiotemporal systems and offer large flexibility in model development as they can incorporate experimental and computational data.
no code implementations • 18 Jun 2023 • Wenzhuo LIU, Mouadh Yagoubi, Marc Schoenauer
To this end, we present a meta-learning approach to enhance the performance of learned models on OoD samples.
no code implementations • 28 Apr 2023 • Alexandre Quemy, Marc Schoenauer, Johann Dreo
Multi-objective AI planning suffers from a lack of benchmarks exhibiting known Pareto Fronts.
no code implementations • 6 Feb 2023 • Matthieu Nastorg, Michele Alessandro Bucci, Thibault Faney, Jean-Marc Gratien, Guillaume Charpiat, Marc Schoenauer
This paper presents $\Psi$-GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions.
no code implementations • 30 Nov 2022 • Emmanuel Menier, Michele Alessandro Bucci, Mouadh Yagoubi, Lionel Mathelin, Thibault Dairay, Raphael Meunier, Marc Schoenauer
Reduced order modeling methods are often used as a mean to reduce simulation costs in industrial applications.
no code implementations • 21 Nov 2022 • Matthieu Nastorg, Marc Schoenauer, Guillaume Charpiat, Thibault Faney, Jean-Marc Gratien, Michele-Alessandro Bucci
This paper proposes a novel Machine Learning-based approach to solve a Poisson problem with mixed boundary conditions.
no code implementations • 8 Jul 2022 • Emmanuel Menier, Michele Alessandro Bucci, Mouadh Yagoubi, Lionel Mathelin, Marc Schoenauer
This paper proposes a novel approach to domain translation.
no code implementations • 22 Feb 2022 • Emmanuel Menier, Michele Alessandro Bucci, Mouadh Yagoubi, Lionel Mathelin, Marc Schoenauer
Model order reduction through the POD-Galerkin method can lead to dramatic gains in terms of computational efficiency in solving physical problems.
no code implementations • 5 Nov 2021 • Mikhail Evchenko, Joaquin Vanschoren, Holger H. Hoos, Marc Schoenauer, Michèle Sebag
Machine learning, already at the core of increasingly many systems and applications, is set to become even more ubiquitous with the rapid rise of wearable devices and the Internet of Things.
1 code implementation • ICLR 2022 • Herilalaina Rakotoarison, Louisot Milijaona, Andry Rasoanaivo, Michele Sebag, Marc Schoenauer
This paper tackles the AutoML problem, aimed to automatically select an ML algorithm and its hyper-parameter configuration most appropriate to the dataset at hand.
no code implementations • 17 May 2021 • Julien Girard-Satabin, Aymeric Varasse, Marc Schoenauer, Guillaume Charpiat, Zakaria Chihani
The impressive results of modern neural networks partly come from their non linear behaviour.
no code implementations • 2 May 2021 • Johann Dreo, Arnaud Liefooghe, Sébastien Verel, Marc Schoenauer, Juan J. Merelo, Alexandre Quemy, Benjamin Bouvier, Jan Gmys
The success of metaheuristic optimization methods has led to the development of a large variety of algorithm paradigms.
no code implementations • 26 Feb 2021 • Aurélie Boisbunon, Carlo Fanara, Ingrid Grenet, Jonathan Daeden, Alexis Vighi, Marc Schoenauer
The Zoetrope Genetic Programming (ZGP) algorithm is based on an original representation for mathematical expressions, targeting evolutionary symbolic regression. The zoetropic representation uses repeated fusion operations between partial expressions, starting from the terminal set.
1 code implementation • NeurIPS 2020 • Balthazar Donon, Zhengying Liu, Wenzhuo LIU, Isabelle Guyon, Antoine Marot, Marc Schoenauer
This paper introduces Deep Statistical Solvers (DSS), a new class of trainable solvers for optimization problems, arising e. g., from system simulations.
no code implementations • 25 Nov 2019 • Julien Girard-Satabin, Guillaume Charpiat, Zakaria Chihani, Marc Schoenauer
We propose to take advantage of the simulators often used either to train machine learning models or to check them with statistical tests, a growing trend in industry.
1 code implementation • 22 Aug 2019 • Benjamin Donnot, Balthazar Donon, Isabelle Guyon, Zhengying Liu, Antoine Marot, Patrick Panciatici, Marc Schoenauer
We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully.
2 code implementations • 1 Jun 2019 • Herilalaina Rakotoarison, Marc Schoenauer, Michèle Sebag
The AutoML task consists of selecting the proper algorithm in a machine learning portfolio, and its hyperparameter values, in order to deliver the best performance on the dataset at hand.
1 code implementation • ICLR 2019 • Alice Schoenauer-Sebag, Louise Heinrich, Marc Schoenauer, Michele Sebag, Lani F. Wu, Steve J. Altschuler
Multi-domain learning (MDL) aims at obtaining a model with minimal average risk across multiple domains.
no code implementations • 27 Feb 2019 • Maryam Hasani-Shoreh, María-Yaneli Ameca-Alducin, Wilson Blaikie, Frank Neumann, Marc Schoenauer
Our proposed framework creates dynamic benchmarks that are flexible in terms of number of changes, dimension of the problem and can be applied to test any objective function.
no code implementations • 3 May 2018 • Benjamin Donnot, Isabelle Guyon, Antoine Marot, Marc Schoenauer, Patrick Panciatici
We address the problem of maintaining high voltage power transmission networks in security at all time, namely anticipating exceeding of thermal limit for eventual single line disconnection (whatever its cause may be) by running slow, but accurate, physical grid simulators.
no code implementations • 3 May 2018 • Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Antoine Marot, Patrick Panciatici
We evaluate that our method scales up to power grids of the size of the French high voltage power grid (over 1000 power lines).
no code implementations • 9 Mar 2018 • Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Lee Altenberg, Julie Beaulieu, Peter J. Bentley, Samuel Bernard, Guillaume Beslon, David M. Bryson, Patryk Chrabaszcz, Nick Cheney, Antoine Cully, Stephane Doncieux, Fred C. Dyer, Kai Olav Ellefsen, Robert Feldt, Stephan Fischer, Stephanie Forrest, Antoine Frénoy, Christian Gagné, Leni Le Goff, Laura M. Grabowski, Babak Hodjat, Frank Hutter, Laurent Keller, Carole Knibbe, Peter Krcah, Richard E. Lenski, Hod Lipson, Robert MacCurdy, Carlos Maestre, Risto Miikkulainen, Sara Mitri, David E. Moriarty, Jean-Baptiste Mouret, Anh Nguyen, Charles Ofria, Marc Parizeau, David Parsons, Robert T. Pennock, William F. Punch, Thomas S. Ray, Marc Schoenauer, Eric Shulte, Karl Sims, Kenneth O. Stanley, François Taddei, Danesh Tarapore, Simon Thibault, Westley Weimer, Richard Watson, Jason Yosinski
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
1 code implementation • 30 Jan 2018 • Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Antoine Marot, Patrick Panciatici
We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers.
no code implementations • 27 Sep 2017 • Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Patrick Panciatici, Antoine Marot
One of the primary goals of dispatchers is to protect equipment (e. g. avoid that transmission lines overheat) with few degrees of freedom: we are considering in this paper solely modifications in network topology, i. e. re-configuring the way in which lines, transformers, productions and loads are connected in sub-stations.
no code implementations • 5 Sep 2017 • Alice Schoenauer-Sebag, Marc Schoenauer, Michèle Sebag
When applied to training deep neural networks, stochastic gradient descent (SGD) often incurs steady progression phases, interrupted by catastrophic episodes in which loss and gradient norm explode.
no code implementations • 10 Jun 2017 • Olivier Bousquet, Sylvain Gelly, Karol Kurach, Marc Schoenauer, Michele Sebag, Olivier Teytaud, Damien Vincent
This paper aims at one-shot learning of deep neural nets, where a highly parallel setting is considered to address the algorithm calibration problem - selecting the best neural architecture and learning hyper-parameter values depending on the dataset at hand.
no code implementations • 27 Oct 2016 • Marti Luis, Fansi-Tchango Arsene, Navarro Laurent, Marc Schoenauer
This paper presents the Voronoi diagram-based evolutionary algorithm (VorEAl).
no code implementations • 19 Jun 2014 • Gaétan Marceau, Marc Schoenauer
In the context of Noisy Multi-Objective Optimization, dealing with uncertainties requires the decision maker to define some preferences about how to handle them, through some statistics (e. g., mean, median) to be used to evaluate the qualities of the solutions, and define the corresponding Pareto set.
no code implementations • 10 Jun 2014 • Ilya Loshchilov, Marc Schoenauer, Michèle Sebag, Nikolaus Hansen
The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is widely accepted as a robust derivative-free continuous optimization algorithm for non-linear and non-convex optimization problems.
no code implementations • 16 Sep 2013 • Gaétan Marceau, Pierre Savéant, Marc Schoenauer
This article addresses the issue of computing the expected cost functions from a probabilistic model of the air traffic flow and capacity management.
no code implementations • 16 Sep 2013 • Gaétan Marceau, Pierre Savéant, Marc Schoenauer
We investigate a method to deal with congestion of sectors and delays in the tactical phase of air traffic flow and capacity management.
no code implementations • 16 Sep 2013 • Gaétan Marceau, Pierre Savéant, Marc Schoenauer
Since air traffic regulations and sector congestion are antagonist, we designed and implemented a multi-objective optimization algorithm for determining the best trade-off between these two criteria.
no code implementations • 12 Aug 2013 • Ilya Loshchilov, Marc Schoenauer, Michèle Sebag
This weakness is commonly addressed through surrogate optimization, learning an estimate of the objective function a. k. a.
no code implementations • 10 May 2013 • Mostepha Redouane Khouadjia, Marc Schoenauer, Vincent Vidal, Johann Dréo, Pierre Savéant
Several meta-optimization methods have been proposed to find the best parameter set for a given optimization algorithm and (set of) problem instances.
no code implementations • 6 May 2013 • Mostepha Redouane Khouadjia, Marc Schoenauer, Vincent Vidal, Johann Dréo, Pierre Savéant
Most real-world Planning problems are multi-objective, trying to minimize both the makespan of the solution plan, and some cost of the actions involved in the plan.
no code implementations • 10 Apr 2013 • François-Michel De Rainville, Michèle Sebag, Christian Gagné, Marc Schoenauer, Denis Laurendeau
At each iteration, the dynamic multi-armed bandit makes a decision on which species to evolve for a generation, using the history of progress made by the different species to guide the decisions.
no code implementations • 5 Aug 2012 • Riad Akrour, Marc Schoenauer, Michèle Sebag
This paper focuses on reinforcement learning (RL) with limited prior knowledge.
1 code implementation • 11 Apr 2012 • Ilya Loshchilov, Marc Schoenauer, Michèle Sebag
The resulting algorithm, saACM-ES, adjusts online the lifelength of the current surrogate model (the number of CMA-ES generations before learning a new surrogate) and the surrogate hyper-parameters.