## About

291

Publications

30,700

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

7,272

Citations

## Publications

Publications (291)

This paper proposes a novel approach to domain translation. Leveraging established parallels between generative models and dynamical systems, we propose a reformulation of the Cycle-GAN architecture. By embedding our model with a Hamiltonian structure, we obtain a continuous, expressive and most importantly invertible generative model for domain tr...

Model order reduction through the POD-Galerkin method can lead to dramatic gains in terms of computational efficiency in solving physical problems. However, the applicability of the method to non linear high-dimensional dynamical systems such as the Navier-Stokes equations has been shown to be limited, producing inaccurate and sometimes unstable mo...

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. In most machine learning applications, the main focus is on the quality of the results achieved (e.g., prediction accuracy), and hence vast amounts of data are...

Deep Learning algorithms have recently received a growing interest to learn from examples of existing solutions and some accurate approximations of the solution of complex physical problems, in particular relying on Graph Neural Networks applied on a mesh of the domain at hand. On the other hand, state-of-the-art deep approaches of image processing...

The success of metaheuristic optimization methods has led to the development of a large variety of algorithm paradigms. However, no algorithm clearly dominates all its competitors on all problems. Instead, the underlying variety of landscapes of optimization problems calls for a variety of algorithms to solve them efficiently. It is thus of prior i...

Recent trends in power systems and those envisioned for the next few decades push Transmission System Operators to develop probabilistic approaches to risk estimation. However, current methods to solve AC power flows are too slow to fully attain this objective. Thus we propose a novel artificial neural network architecture that achieves a more suit...

This book constitutes the thoroughly refereed post-conference proceedings of the 14th International Conference on Artificial Evolution, EA 2019, held in Mulhouse, France, in October 2019.
The 16 revised papers were carefully reviewed and selected from 33 submissions. The papers cover a wide range of topics in the field of artificial evolution, such...

Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: Artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of ev...

Self-driving cars and advanced driver-assistance systems are perceived as a game-changer in the future of road transportation. However, their validation is mandatory before industrialization; testing every component should be assessed intensively in order to mitigate potential failures and avoid unwanted problems on the road. In order to cover all...

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. We call our architeture LEAP net, for Latent Encoding of Atypical Perturbation. Our method implements a form of transfer learning,...

The AutoML approach aims to deliver peak performance from a machine learning portfolio on the dataset at hand. A Monte-Carlo Tree Search Algorithm Selection and Configuration (Mosaic) approach is presented to tackle this mixed (combinatorial and continuous) expensive optimization problem on the structured search space of ML pipelines. Extensive les...

The study of semantics in Genetic Programming (GP) has increased dramatically over the last years due to the fact that researchers tend to report a performance increase in GP when semantic diversity is promoted. However, the adoption of semantics in Evolutionary Multi-objective Optimisation (EMO), at large, and in Multi-objective GP (MOGP), in part...

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. Mosaic, a Monte-Carlo tree search (MCTS) based approach, is presented to handle the AutoML hybrid structural and parametric expensive black-box optimization probl...

Multi-domain learning (MDL) aims at obtaining a model with minimal average risk across multiple domains. Our empirical motivation is automated microscopy data, where cultured cells are imaged after being exposed to known and unknown chemical perturbations, and each dataset displays significant experimental bias. This paper presents a multi-domain a...

Evolutionary algorithms have been widely applied for solving dynamic constrained optimization problems (DCOPs) as a common area of research in evolutionary optimization. Current benchmarks proposed for testing these problems in the continuous spaces are either not scalable in problem dimension or the settings for the environmental changes are not f...

Evolutionary algorithms have been widely applied for solving dynamic constrained optimization problems (DCOPs) as a common area of research in evolutionary optimization. Current benchmarks proposed for testing these problems in the continuous spaces are either not scalable in problem dimension or the settings for the environmental changes are not f...

Algorithm portfolios are known to offer robust performances, efficiently overcoming the weakness of every single algorithm on some particular problem instances. Two complementary approaches to get the best out of an algorithm portfolio are to achieve algorithm selection (AS), and to define a scheduler, sequentially launching a few algorithms on a l...

Using neural network modeling, we address the problem system identification for continuous multivariate systems, whose structures vary around an operating point. Structural changes in the system are of combinatorial nature, and some of them may be very rare; they may be actionable for the purpose of controlling the system. Although our ultimate goa...

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. New conceptual frameworks are calling for a probabilistic risk-based securi...

We address the problem of maintaining high voltage power transmission networks in security at all time. This requires that power flowing through all lines remain below a certain nominal thermal limit above which lines might melt, break or cause other damages. Current practices include enforcing the deterministic "N-1" reliability criterion, namely...

Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic process that transcends the substrate in which it occurs, evolution's creativity is not limited to nature. Indeed, many researchers in the field of digital evolution have o...

Character recognition plays an important role in the modern world. In recent years, character recognition systems for different languages has gain importance. The recognition of Arabic writing is still an important challenge due to its cursive nature and great topological variability. The Artificial Immune System is a supervised learning technique...

13th International Conference, Évolution Artificielle, EA 2017, Paris, France, October 25–27, 2017, Revised Selected Papers

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. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to tr...

This book constitutes the thoroughly refereed post-conference proceedings of the 13th International Conference on Artificial Evolution, EA 2017, held in Paris, France, in October 2017.
The 16 revised papers were carefully reviewed and selected from 33 submissions. The papers cover a wide range of topics in the field of artificial evolution, such a...

In this paper, we investigate the use of an stochastic optimisation bio-inspired algorithm, differential evolution, and proposed two fitness (cost) functions that can automatically create an intelligent scheduling for a demand-side management system so that it can use plug-in electric vehicles’s (PEVs) batteries to partially and temporarily fulfil...

We address the problem of assisting human dispatchers in operating power grids in today's changing context using machine learning, with theaim of increasing security and reducing costs. Power networks are highly regulated systems, which at all times must meet varying demands of electricity with a complex production system, including conventional po...

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. A possible mitigation of such events is to slow down the learning process. This paper presents a novel approach to control the SGD learning rate, that...

In Genetic Programming (GP), the fitness of individuals is normally computed by using a set of fitness cases (FCs). Research on the use of FCs in GP has primarily focused on how to reduce the size of these sets to, for instance, reduce the fitness evaluation time. However, often, only a small set of FCs is available and there is no need to reduce i...

One of the principles of evolutionary multi-objective optimization is the conjoint optimization of the objective functions. However, in some cases, some of the objectives are easier to attain than others. This causes the population to lose diversity at a high rate and stagnate in early stages of the evolution. This paper presents the progressive ad...

Per Instance Algorithm Configuration (PIAC) relies on features that describe problem instances. It builds an Empirical Performance Model (EPM) from a training set made of (instance, parameter configuration) pairs together with the corresponding performance of the algorithm at hand. This paper presents a case study in the continuous black-box optimi...

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. The notoriously expensive calibration problem is optimally reduced by detecting and early...

This paper presents the Voronoi diagram-based evolutionary algorithm (VorEAl). VorEAl partitions input space in abnormal/normal subsets using Voronoi diagrams. Diagrams are evolved using a multi-objective bio-inspired approach in order to conjointly optimize classification metrics while also being able to represent areas of the data space that are...

The Anti Imitation-based Policy Learning (AIPoL) approach, taking inspiration from the Energy-based learning framework (LeCun et al. 2006), aims at a pseudo-value function such that it induces the same order on the state space as a (nearly optimal) value function. By construction, the greedification of such a pseudo-value induces the same policy as...

Research on semantics in Genetic Programming (GP) has increased dramatically over the last number of years. Results in this area clearly indicate that its use in GP can considerably increase GP performance. Motivated by these results, this paper investigates for the first time the use of Semantics in Muti-objective GP within the well-known NSGA-II...

This paper presents the Voronoi diagram-based evolutionary algorithm (VorEAl). VorEAl partitions input space in abnormal/normal subsets using Voronoi diagrams. Diagrams are evolved using a multi-objective bio-inspired approach in order to conjointly optimize classification metrics while also being able to represent areas of the data space that are...

Algorithm Configuration is still an intricate problem especially in the continuous black box optimization domain. This paper empirically investigates the relationship between continuous problem features (measuring different problem characteristics) and the best parameter configuration of a given stochastic algorithm over a bench of test functions —...

This paper introduces the Voronoi diagram-based Artificial Immune System (VorAIS). VorAIS models the self/non-self using a Voronoi diagram that determines which areas of the problem domain correspond to self or to non-self. The diagram is evolved using a multi-objective bio-inspired approach in order to conjointly optimize various classification me...

A possible approach to Algorithm Selection and Configuration for continuous black box optimization problems relies on problem features, computed from a set of evaluated sample points. However, the computation of these features requires a rather large number of such samples, unlikely to be practical for expensive real-world problems.
On the other h...

Semantic Backpropagation (SB) was introduced in GP so as to take into account the semantics of a GP tree at all intermediate states of the program execution, i.e., at each node of the tree. The idea is to compute the optimal “should-be” values each subtree should return, whilst assuming that the rest of the tree is unchanged, and to choose a subtre...

This book constitutes the thoroughly refereed post-conference proceedings of the 12th International Conference on Artificial Evolution, EA 2015, held in Lyon, France, in October 2015.
The 18 revised papers were carefully reviewed and selected from 31 submissions. The focus of the conference is on following topics: Evolutionary Computation, Evolutio...

The goal of this paper is to investigate on the overall performance of CMA-ES, when dealing with a large number of cores — considering the direct mapping between cores and individuals — and to empirically find the best parameter strategies for a parallel machine. By considering the problem of parameter setting, we empirically determine a new strate...

This chapter presents the fi eld of evolutionary algoithms, that is, Darwininspired algorithms used to fi nd approximate optimal solutions to some problems, that are not easily, or not all, likely to be reached by traditionnal optimisation methods. After a presentation of the basics of evolutionary algorithms, their conceptual tools and their vocab...

Semantic Backpropagation (SB) was introduced in GP so as to take into account the semantics of a GP tree at all intermediate states of the program execution, i.e., at each node of the tree. The idea is to compute the optimal "should-be" values each subtree should return, whilst assuming that the rest of the tree is unchanged, so as to minimize the...

Semantic Backpropagation (SB) was introduced in GP so as to take into account the semantics of a GP tree at all intermediate states of the program execution, i.e., at each node of the tree. The idea is to compute the optimal "should-be" values each subtree should return, whilst assuming that the rest of the tree is unchanged, and to choose a subtre...

This paper advocates a new ML-based programming framework, called Programming by Feedback (PF), which involves a sequence of interactions between the active computer and the user. The latter only provides preference judgments on pairs of solutions supplied by the active computer. The active computer involves two components: The learning component e...

This book constitutes the refereed proceedings of the 11th International Conference on Artificial Evolution, EA 2013, held in Bordeaux, France, in October 2013.
The 20 revised papers were carefully reviewed and selected from 39 submissions. The papers are focused to theory, ant colony optimization, applications, combinatorial and discrete optimiza...

Constraint Programming (CP) solvers classically explore the solution space using tree-search based heuristics. MonteCarlo Tree-Search (MCTS) is a tree-search method aimed at optimal sequential decision making under uncertainty. At the crossroads of CP and MCTS, this paper presents the Bandit Search for Constraint Programming (BASCOP) algorithm, ada...

With the objective of handling the airspace sector congestion subject to continuously growing air traffic, we suggest
to create a collaborative working plan during the strategic phase of air traffic control. The plan obtained via a new decisionsupport tool presented in this article consists in a schedule for controllers, which specifies time of ove...

In this paper, we investigate a method to deal with congestion of sectors and delays in the pre-tactical phase of air traffic control. It relies on the paradigm change from calculated time of takeoff to target time of arrival studied in the SESAR programme. In our case, targets are given for every point of the flight plans and are shared among the...

Constraint Programming (CP) solvers classically explore the solution space using tree search-based heuristics. Monte-Carlo Tree-Search (MCTS), a tree-search based method aimed at sequential decision making under uncertainty, simultaneously estimates the reward associated to the sub-trees, and gradually biases the exploration toward the most promisi...

Six population-based methods for real-valued black box optimization are thoroughly compared in this article. One of them, Nelder-Mead simplex search, is rather old, but still a popular technique of direct search. The remaining five POEMS, G3PCX, Cauchy ...

Nowadays, huge efforts are made to modernize the air traffic management systems to cope with uncertainty, complexity and sub-optimality. An answer is to enhance the information sharing between the stakeholders. This paper introduces a framework that bridges the gap between air traffic management and air traffic control on the one hand, and bridges...

This paper presents a model based on an hybrid system to numerically simulate the climbing phase of an aircraft. This model is then used within a trajectory prediction tool. Finally, the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) optimization algorithm is used to tune five selected parameters, and thus improve the accuracy of the mode...

Parallel master-slave evolutionary algorithms easily lead to linear speedups in the case of a small number of nodes... and homogeneous computational costs of the evaluations. However, modern computer now routinely have several hundreds of nodes - and in many real-world applications in which fitness computation involves heavy numerical simulations,...

Among the most promising and active research areas in heuristic optimisation is the field of adaptive memetic algorithms (AMAs). These gain much of their reported robustness by adapting the probability with which each of a set of local improvement operators ...

Learn-and-Optimize (LaO) is a generic surrogate based method for parameter tuning combining learning and optimization. In this paper LaO is used to tune Divide-and-Evolve (DaE), an Evolutionary Algorithm for AI Planning. The LaO framework makes it possi-ble to learn the relation between some features describ-ing a given instance and the optimal par...

The ancient oriental game of Go has long been considered a grand challenge for artificial intelligence. For decades, computer Go has defied the classical methods in game tree search that worked so successfully for chess and checkers. How- ever, recent play in computer Go has been transformed by a new paradigm for tree search based on Monte-Carlo me...

One of the settings that most affect the performance of Evolutionary Algorithms is the selection of the variation operators that are efficient to solve the problem at hand. The control of these operators can be handled in an autonomous way, while solving the problem, at two different levels: at the structural level, when deciding which operators sh...