arXiv subjects

Claude Guet

Publications and source records attributed to Claude Guet.

8 recordsLinked to original sources

arXiv2026

Differential-Embedding Reconstruction of Dynamical Systems from Scalar Time Series

We study the reconstruction of an unknown dynamical system from a single noisy scalar time series. The goal is to recover the underlying dynamics for forecasting. We introduce a method that uses differential embedding coordinates to identify a rational closure of the embedding dynamics directly from data. The closure is identified through a weak-form regression pipeline, which avoids unstable pointwise differentiation of noisy data. When applied to noise-free Lorenz and R\"ossler systems, the method recovers closures that support long forecasts across a broad ensemble of realizations ($18.1$ and $7.1$ Lyapunov times respectively). Under $15$--$30\%$ additive Gaussian noise, performance becomes system-dependent. For the Lorenz system, forecast horizons remain short even in the best cases, whereas the R\"ossler system generally performs better in absolute terms, though not once normalized by the Lyapunov time. Our proposed method recovers directly interpretable closure coefficients which we compared against the known analytic closures of the Lorenz and R\"ossler systems.

physics.comp-ph↗

arXiv2026

Surrogate modeling of drift-reduced Braginskii turbulence with resistivity-conditioned Koopman neural operators

Machine-learning-driven surrogate operators are developed for three-dimensional, nonlinear, flux-driven simulations of boundary plasma turbulence based on the two-fluid drift-reduced Braginskii model. Resistivity-conditioned Koopman neural operators (KNOs) are trained on Global Braginskii Solver (GBS) simulations, spanning low- to high-resistivity regimes. Separate fieldwise models are constructed for plasma density, electron temperature, electric potential, and vorticity. Evaluation at a held-out resistivity shows that the surrogates reproduce key short-horizon statistical features, including strong one-step agreement, spectral trends, and reduced pressure-gradient diagnostics. Field-dependent limitations remain, with vorticity showing the largest discrepancies and autoregressive rollout progressively departing from the reference simulation. The results demonstrate that resistivity-conditioned fieldwise neural operators provide useful fast emulators for selected boundary-plasma turbulence diagnostics, while stable long-horizon dynamical closure remains unresolved.

physics.plasm-ph↗

arXiv2025

Hybrid Neural Interpolation of a Sequence of Wind Flows

Rapid and accurate urban wind field prediction is essential for modeling particle transport in emergency scenarios. Traditional Computational Fluid Dynamics (CFD) approaches are too slow for real-time applications, necessitating surrogate models. We develop a hybrid neural interpolation method for constructing surrogate models that can update urban wind maps on timescales aligned with meteorological variations. Our approach combines Tucker tensor decomposition with neural networks to interpolate Reynolds-Averaged Navier-Stokes (RANS) solutions across varying inlet wind angles. The method decomposes high-dimensional velocity, pressure, and eddy viscosity field datasets into a core tensor and factor matrices, then uses Fourier interpolation for angular modes and k-nearest neighbors convolution for spatial interpolation. A neural network correction mitigates interpolation artifacts while preserving physical consistency. We validate the approach on a simple cylinder-sphere configuration and, relative to a strong pure neural network benchmark, achieve comparable or improved accuracy ($R^2 > 0.99$) with significantly reduced training time. The pure NN remains a feasible reference model; the hybrid provides an accelerated approximate alternative that suppresses spurious oscillations, maintains wake dynamics, and demonstrates computational efficiency suitable for real-time urban wind simulation.

physics.comp-ph↗

arXiv2022

Joint Optimization of Energy Consumption and Completion Time in Federated Learning

Federated Learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. To balance the trade-off between energy and execution latency, and thus accommodate different demands and application scenarios, we formulate an optimization problem to minimize a weighted sum of total energy consumption and completion time through two weight parameters. The optimization variables include bandwidth, transmission power and CPU frequency of each device in the FL system, where all devices are linked to a base station and train a global model collaboratively. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, and CPU frequency for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm not only has better performance at different weight parameters (i.e., different demands) but also outperforms the state of the art.

cs.LG↗

arXiv2021

Deep self-consistent learning of local volatility

We present an algorithm for the calibration of local volatility from market option prices through deep self-consistent learning, by approximating both market option prices and local volatility using deep neural networks. Our method uses the initial-boundary value problem of the underlying Dupire's partial differential equation solved by the parameterized option prices to bring corrections to the parameterization in a self-consistent way. By exploiting the differentiability of neural networks, we can evaluate Dupire's equation locally at each strike-maturity pair; while by exploiting their continuity, we sample strike-maturity pairs uniformly from a given domain, going beyond the discrete points where the options are quoted. Moreover, the absence of arbitrage opportunities are imposed by penalizing an associated loss function as a soft constraint. For comparison with existing approaches, the proposed method is tested on both synthetic and market option prices, which shows an improved performance in terms of reduced interpolation and reprice errors, as well as the smoothness of the calibrated local volatility. An ablation study has been performed, asserting the robustness and significance of the proposed method.

q-fin.CP↗

arXiv2021

Reconstructing a dynamical system and forecasting time series by self-consistent deep learning

We introduce a self-consistent deep-learning framework which, for a noisy deterministic time series, provides unsupervised filtering, state-space reconstruction, identification of the underlying differential equations and forecasting. Without a priori information on the signal, we embed the time series in a state space, where deterministic structures, i.e. attractors, are revealed. Under the assumption that the evolution of solution trajectories is described by an unknown dynamical system, we filter out stochastic outliers. The embedding function, the solution trajectories and the dynamical systems are constructed using deep neural networks, respectively. By exploiting the differentiability of the neural solution trajectory, the neural dynamical system is defined locally at each time, mitigating the need for propagating gradients through numerical solvers. On a chaotic time series masked by additive Gaussian noise, we demonstrate the filtering ability and the predictive power of the proposed framework.

cs.LG↗

arXiv2021

Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field

Solving physics problems for which we know the equations, boundary conditions and symmetries can be done by deep learning. The constraints can be either imposed as terms in a loss function or used to formulate a neural ansatz. In the present case study, we calculate the induced field inside and outside a dielectric cube placed in a uniform electric field, wherein the dielectric mismatch at edges and corners of the cube makes accurate calculations numerically challenging. The electric potential is expressed as an ansatz incorporating neural networks with known leading order behaviors and symmetries and the Laplace's equation is then solved with boundary conditions at the dielectric interface by minimizing a loss function. The loss function ensures that both Laplace's equation and boundary conditions are satisfied everywhere inside a large solution domain. We study how the electric potential inside and outside a quasi-cubic particle evolves through a sequence of shapes from a sphere to a cube. The neural network being differentiable, it is straightforward to calculate the electric field over the whole domain, the induced surface charge distribution and the polarizability. The neural network being retentive, one can efficiently follow how the field changes upon particle's shape or dielectric constant by iterating from any previously converged solution. The present work's objective is two-fold, first to show how an a priori knowledge can be incorporated into neural networks to achieve efficient learning and second to apply the method and study how the induced field and polarizability change when a dielectric particle progressively changes its shape from a sphere to a cube.

physics.class-ph↗

arXiv2018

From quantum to classical dipole plasmon resonances in highly-doped nano-crystals

Dipole plasmon resonances are ubiquitous in nano-particles with delocalized charge carriers. Doped semi-conductor colloidal nano-crystals constitute a novel paradigm for plasmon excitations in a finite electron system and offer the possibility to tune the carrier density and thus the dipole resonance from visible to infra-red, which cannot be achieved with metallic clusters. Restricting ourselves to highly n-doped ZnO nano-crystals, we explain the observed smooth transition from small sizes dominated by quantum effects to large sizes where the resonance reaches its classical value. A schematic two interacting highly degenerate level quantum model, validated by a full Random Phase Approximation calculation, yields nicely the experimentally observed trends.

physics.atm-clus↗