arXiv subjects

Ani Anciaux-Sedrakian

Publications and source records attributed to Ani Anciaux-Sedrakian.

4 recordsLinked to original sources

arXiv2023

waLBerla-wind: a lattice-Boltzmann-based high-performance flow solver for wind energy applications

This article presents the development of a new wind turbine simulation software to study wake flow physics. To this end, the design and development of waLBerla-wind, a new simulator based on the lattice-Boltzmann method that is known for its excellent performance and scaling properties, will be presented. Here it will be used for large eddy simulations (LES) coupled with actuator wind turbine models. Due to its modular software design, waLBerla-wind is flexible and extensible with regard to turbine configurations. Additionally it is performance portable across different hardware architectures, another critical design goal. The new solver is validated by presenting force distributions and velocity profiles and comparing them with experimental data and a vortex solver. Furthermore, waLBerla-wind's performance is \revision{compared to a theoretical peak performance}, and analysed with weak and strong scaling benchmarks on CPU and GPU systems. This analysis demonstrates the suitability for large-scale applications and future cost-effective full wind farm simulations.

cs.CE↗

arXiv2023

Analysis and Comparison of Two-Level KFAC Methods for Training Deep Neural Networks

As a second-order method, the Natural Gradient Descent (NGD) has the ability to accelerate training of neural networks. However, due to the prohibitive computational and memory costs of computing and inverting the Fisher Information Matrix (FIM), efficient approximations are necessary to make NGD scalable to Deep Neural Networks (DNNs). Many such approximations have been attempted. The most sophisticated of these is KFAC, which approximates the FIM as a block-diagonal matrix, where each block corresponds to a layer of the neural network. By doing so, KFAC ignores the interactions between different layers. In this work, we investigate the interest of restoring some low-frequency interactions between the layers by means of two-level methods. Inspired from domain decomposition, several two-level corrections to KFAC using different coarse spaces are proposed and assessed. The obtained results show that incorporating the layer interactions in this fashion does not really improve the performance of KFAC. This suggests that it is safe to discard the off-diagonal blocks of the FIM, since the block-diagonal approach is sufficiently robust, accurate and economical in computation time.

cs.LG↗

arXiv2023

Computing Surface Reaction Rates by Adaptive Multilevel Splitting Combined with Machine Learning and Ab Initio Molecular Dynamics

Computing accurate rate constants for catalytic events occurring at the surface of a given material represents a challenging task with multiple potential applications in chemistry. To address this question, we propose an approach based on a combination of the rare event sampling method called Adaptive Multilevel Splitting (AMS) and ab initio molecular dynamics (AIMD). The AMS method requires a one dimensional reaction coordinate to index the progress of the transition. Identifying a good reaction coordinate is difficult, especially for high dimensional problems such a those encountered in catalysis. We probe various approaches to build reaction coordinates such as Support Vector Machine and path collective variables. The AMS is implemented so as to communicate with a DFT-plane wave code. A relevant case study in catalysis: the change of conformation and the dissociation of a water molecule chemisorbed on the (100) $γ$-alumina surface is used to evaluate our approach. The calculated rate constants and transition mechanisms are discussed and compared to those obtained by a conventional static approach based on the Eyring-Polanyi equation with harmonic approximation. It is revealed that the AMS method may provide rate constants which are smaller than the static approach by up to two orders of magnitude due to entropic effects involved in the chemisorbed water.

physics.chem-ph↗

arXiv2022

Efficient Approximations of the Fisher Matrix in Neural Networks using Kronecker Product Singular Value Decomposition

Several studies have shown the ability of natural gradient descent to minimize the objective function more efficiently than ordinary gradient descent based methods. However, the bottleneck of this approach for training deep neural networks lies in the prohibitive cost of solving a large dense linear system corresponding to the Fisher Information Matrix (FIM) at each iteration. This has motivated various approximations of either the exact FIM or the empirical one. The most sophisticated of these is KFAC, which involves a Kronecker-factored block diagonal approximation of the FIM. With only a slight additional cost, a few improvements of KFAC from the standpoint of accuracy are proposed. The common feature of the four novel methods is that they rely on a direct minimization problem, the solution of which can be computed via the Kronecker product singular value decomposition technique. Experimental results on the three standard deep auto-encoder benchmarks showed that they provide more accurate approximations to the FIM. Furthermore, they outperform KFAC and state-of-the-art first-order methods in terms of optimization speed.

cs.NE↗