RCReda Chhaibi

Reda Chhaibi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Reda Chhaibi has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • To spike or not to spike: the whims of the Wonham filter in the strong noise regime

    by Cédric Bernardin, Reda Chhaibi, Joseph Najnudel, Clément Pellegrini

  • On the circle, Gaussian multiplicative chaos and Beta ensembles match exactly

    by Reda Chhaibi, Joseph Najnudel

    We identify an equality between two objects arising from different contexts of mathematical physics: Kahane’s Gaussian multiplicative chaos ( GMC^{\gamma} ) on the circle and the circular Beta ensemble (C\beta E) from random matrix theory. This is obtained via an analysis of related random orthogonal polynomials, making the approach spectral in nature. In order for the equality to hold, the simple relationship between coupling constants is \gamma = \sqrt{{2}/{\beta}} , which we establish when \gamma \leq 1 or equivalently \beta \geq 2 . This corresponds to the subcritical and critical phases for GMC^{\gamma} . As a side product, we answer positively a question raised by Virág, on the fractal spectrum of a random measure constructed from C \beta E . We also give an alternative proof of the Fyodorov–Bouchaud formula concerning the total mass of GMC^{\gamma} on the circle. This conjecture was recently settled by Remy using Liouville conformal field theory. We can go even further and give an explicit description of the Fourier coefficients of the random measure GMC^{\gamma} in terms of independent Beta random variables. Furthermore, we notice that the “spectral construction” has a few advantages. For example, the Hausdorff dimension of the support is efficiently described for all \beta>0 , thanks to existing spectral theory. Remarkably, the critical parameter for GMC^{\gamma} corresponds to \beta=2 , where the geometry and representation theory of unitary groups lie.


  • Open Access

    Algebra of Nonlocal Boxes and the Collapse of Communication Complexity

    by Pierre Botteron, Anne Broadbent, Reda Chhaibi, Ion Nechita, Clément Pellegrini

    Communication complexity quantifies how difficult it is for two distant computers to evaluate a functionf(X,Y), where the stringsXandYare distributed to the first and second computer respectively, under the constraint of exchanging as few bits as possible. Surprisingly, some nonlocal boxes, which are resources shared by the two computers, are so powerful that they allow tocollapsecommunication complexity, in the sense that any Boolean function f can be correctly estimated with the exchange of only one bit of communication. The Popescu-Rohrlich (PR) box is an example of such a collapsing resource, but a comprehensive description of the set of collapsing nonlocal boxes remains elusive.In this work, we carry out an algebraic study of the structure of wirings connecting nonlocal boxes, thus defining the notion of the "product of boxes"P⊠Q, and we show related associativity and commutativity results. This gives rise to the notion of the "orbit of a box", unveiling surprising geometrical properties about the alignment and parallelism of distilled boxes. The power of this new framework is that it allows us to prove previously-reported numerical observations concerning the best way to wire consecutive boxes, and to numerically and analytically recover recently-identified noisyPRboxes that collapse communication complexity for different types of noise models.


  • Open Access

    Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits

    by Reda Chhaibi, Fabrice Gamboa, Christophe Oger, Vinicius Oliveira, Clément Pellegrini, Damien Remot

    We propose an active sampling flow, with the use-case of simulating the impact of combined variations on analog circuits. In such a context, given the large number of parameters, it is difficult to fit a surrogate model and to efficiently explore the space of design features. By combining a drastic dimension reduction using sensitivity analysis and Bayesian surrogate modeling, we obtain a flexible active sampling flow. On synthetic and real datasets, this flow outperforms the usual Monte-Carlo sampling which often forms the foundation of design space exploration.

  • Open Access

    Scattering of the Toda system and the Gaussian $β$-ensemble

    by Reda Chhaibi

    The classical Toda flow is a well-known integrable Hamiltonian system that diagonalizes matrices. By keeping track of the distribution of entries and precise scattering asymptotics, one can exhibit matrix models for log-gases on the real line. These types of scattering asymptotics date back to fundamental work of Moser. More precisely, using the classical Toda flow acting on symmetric real tridiagonal matrices, we give a "symplectic" proof of the fact that the Dumitriu-Edelman tridiagonal model has a spectrum following the Gaussian $β$-ensemble.

  • Open Access

    Estimation of large covariance matrices via free deconvolution: computational and statistical aspects

    by Reda Chhaibi, Fabrice Gamboa, Slim Kammoun, Mauricio Velasco

    The estimation of large covariance matrices has a high dimensional bias. Correcting for this bias can be reformulated via the tool of Free Probability Theory as a free deconvolution. The goal of this work is a computational and statistical resolution of this problem. Our approach is based on complex-analytic methods methods to invert $S$-transforms. In particular, one needs a theoretical understanding of the Riemann surfaces where multivalued $S$ transforms live and an efficient computational scheme.

  • Open Access

    To spike or not to spike: the whims of the Wonham filter in the strong noise regime

    by Cédric Bernardin, Reda Chhaibi, Joseph Najnudel, Clément Pellegrini

    We study the celebrated Shiryaev-Wonham filter in its historical setup of Wonham (1964) where the hidden Markov jump process has two states. We are interested in the weak noise regime for the observation equation. Interestingly, this becomes a strong noise regime for the filtering equations. Earlier results of the authors show the appearance of spikes in the filtered process, akin to a metastability phenomenon. This paper is aimed at understanding the smoothed optimal filter, which is relevant for any system with feedback. In particular, we demonstrate that there is a sharp phase transition between a spiking regime and a regime with perfect smoothing.

  • Spiking and collapsing in large noise limits of SDEs

    by Cédric Bernardin, Raphaël Chetrite, Reda Chhaibi, Joseph Najnudel, Clément Pellegrini

    We analyze the strong noise limit of one-dimensional stochastic differential equations (SDEs). Our initial motivation comes from continuous measurements of open quantum systems. In this context, Bauer, Bernard and Tilloy pointed out an intriguing behavior. As the noise grows larger, the solutions exhibit locally a collapsing, that is to say, converge to pure jump processes very reminiscent of a metastability phenomenon. But surprisingly the limiting jump process is decorated by a spike process. We give a precise meaning to the convergence and completely prove these statements for a large class of one-dimensional diffusions, thanks to a robust strategy of proof.


  • Open Access

    Free Probability for predicting the performance of feed-forward fully connected neural networks

    by Reda Chhaibi, Tariq Daouda, Ezechiel Kahn

    Gradient descent during the learning process of a neural network can be subject to many instabilities. The spectral density of the Jacobian is a key component for analyzing stability. Following the works of Pennington et al., such Jacobians are modeled using free multiplicative convolutions from Free Probability Theory (FPT). We present a reliable and very fast method for computing the associated spectral densities, for given architecture and initialization. This method has a controlled and proven convergence. Our technique is based on an homotopy method: it is an adaptative Newton-Raphson scheme which chains basins of attraction. In order to demonstrate the relevance of our method we show that the relevant FPT metrics computed before training are highly correlated to final test accuracies - up to 85\%. We also nuance the idea that learning happens at the edge of chaos by giving evidence that a very desirable feature for neural networks is the hyperbolicity of their Jacobian at initialization.

  • Open Access

    Emergence of jumps in quantum trajectories via homogeneization

    by Tristan Benoist, Cédric Bernardin, Raphaël Chetrite, Reda Chhaibi, Joseph Najnudel, Clément Pellegrini

    In the strong noise regime, we study the homogeneization of quantum trajectories i.e. stochastic processes appearing in the context of quantum measurement. When the generator of the average semi-group can be separated into three distinct time scales, we start by describing a homogenized limiting semi-group. This result is of independent interest and is formulated outside of the scope of quantum trajectories. Going back to the quantum context, we show that, in the Meyer-Zheng topology, the time-continuous quantum trajectories converge weakly to the discontinuous trajectories of a pure jump Markov process. Notably, this convergence cannot hold in the usual Skorokhod topology.