English
Related papers

Related papers: Backpropagation in hyperbolic chaos via adjoint sh…

200 papers

We devise the fast adjoint response algorithm for the gradient of physical measures (long-time-average statistics) of discrete-time hyperbolic chaos with respect to many system parameters. Its cost is independent of the number of…

Dynamical Systems · Mathematics 2022-09-13 Angxiu Ni

For hyperbolic diffeomorphisms, we define adjoint shadowing directions as a bounded inhomogeneous adjoint solution whose initial condition has zero component in the unstable adjoint direction. For hyperbolic flows, we define adjoint…

Dynamical Systems · Mathematics 2019-05-14 Angxiu Ni

Nonintrusive shadowing algorithms efficiently compute $v$, the difference between shadowing trajectories, then use $v$ to compute derivatives of averaged objectives of chaos with respect to parameters of the dynamical system. However,…

Dynamical Systems · Mathematics 2021-11-16 Angxiu Ni

Adjoint-based sensitivity analysis is of interest in computational science due to its ability to compute sensitivities at a lower cost with respect to several design parameters. However, conventional sensitivity analysis methods fail in the…

Numerical Analysis · Mathematics 2025-07-15 Pranshul Thakur , Siva Nadarajah

In a uniformly hyperbolic system, we consider the problem of finding the optimal infinitesimal perturbation to apply to the system, from a certain set $P$ of feasible ones, to maximally increase the expectation of a given observation…

Dynamical Systems · Mathematics 2025-01-07 Stefano Galatolo , Angxiu Ni

The sensitivity of long-time averages of a hyperbolic chaotic system to parameter perturbations can be determined using the shadowing direction, the uniformly-bounded-in-time solution of the sensitivity equations. Although its existence is…

Chaotic Dynamics · Physics 2019-05-22 Davide Lasagna , Ati Sharma , Johan Meyers

Chaotic dynamical systems are characterized by the sensitive dependence of trajectories on initial conditions. Conventional sensitivity analysis of time-averaged functionals yields unbounded sensitivities when the simulation is chaotic. The…

Numerical Analysis · Mathematics 2025-02-17 Pranshul Thakur , Siva Nadarajah

Models with dominant advection always posed a difficult challenge for projection-based reduced order modelling. Many methodologies that have recently been proposed are based on the pre-processing of the full-order solutions to accelerate…

Numerical Analysis · Mathematics 2022-03-02 Davide Papapicco , Nicola Demo , Michele Girfoglio , Giovanni Stabile , Gianluigi Rozza

Backpropagation algorithm is the cornerstone for neural network analysis. Paper extends it for training any derivatives of neural network's output with respect to its input. By the dint of it feedforward networks can be used to solve or…

Neural and Evolutionary Computing · Computer Science 2017-12-13 V. I. Avrutskiy

In this paper, we investigate the limiting behavior of a continuous-time counterpart of the Stochastic Gradient Descent (SGD) algorithm applied to two-layer overparameterized neural networks, as the number or neurons (ie, the size of the…

Machine Learning · Statistics 2020-07-15 Valentin De Bortoli , Alain Durmus , Xavier Fontaine , Umut Simsekli

If a nonnegative selfadjoint linear relation $A$ in a Hilbert space and a closed subspace $\mathcal{S}$ are assumed to satisfy that the domain of $A$ is invariant under the orthogonal projector onto $\mathcal{S},$ then $A$ admits a…

Functional Analysis · Mathematics 2021-08-25 Maximiliano Contino , Alejandra Maestripieri , Stefania Marcantognini

This paper presents a concise mathematical framework for investigating both feed-forward and backward process, during the training to learn model weights, of an artificial neural network (ANN). Inspired from the idea of the two-step rule…

Neural and Evolutionary Computing · Computer Science 2023-05-02 Ahmed Boughammoura

We derive and prove the `fast response' formula for the linear response, the parameter derivatives of long-time-averaged statistics, of hyperbolic deterministic chaotic systems. The expression is pointwisely defined so we can compute the…

Dynamical Systems · Mathematics 2025-12-15 Angxiu Ni

Embedding discrete solvers as differentiable layers has given modern deep learning architectures combinatorial expressivity and discrete reasoning capabilities. The derivative of these solvers is zero or undefined, therefore a meaningful…

Machine Learning · Computer Science 2024-12-16 Subham Sekhar Sahoo , Anselm Paulus , Marin Vlastelica , Vít Musil , Volodymyr Kuleshov , Georg Martius

We study the asymptotic behavior of Lipschitz continuous solutions of nonlinear degenerate parabolic equations in the periodic setting. Our results apply to a large class of Hamilton-Jacobi-Bellman equations. Defining S as the set where the…

Analysis of PDEs · Mathematics 2013-06-05 Olivier Ley , Vinh Duc Nguyen

We show that linear chaos in the space $c(\mathbb{N})$ of convergent sequences cannot be arrived at by merely extending the weighted backward shifts in the space $c_0(\mathbb{N})$ of vanishing sequences. Applying a newly found sufficient…

Functional Analysis · Mathematics 2022-04-05 Marat V. Markin , Gabriel Martinez Lazaro , Edward S. Sichel

We analyze the convergence of the one-level overlapping domain decomposition preconditioner SORAS (Symmetrized Optimized Restricted Additive Schwarz) applied to a generic linear system whose matrix is not necessarily symmetric/self-adjoint…

Numerical Analysis · Mathematics 2024-08-06 Marcella Bonazzoli , Xavier Claeys , Frédéric Nataf , Pierre-Henri Tournier

We introduce backdrop, a flexible and simple-to-implement method, intuitively described as dropout acting only along the backpropagation pipeline. Backdrop is implemented via one or more masking layers which are inserted at specific points…

Machine Learning · Statistics 2018-06-06 Siavash Golkar , Kyle Cranmer

A recent paper by Boughammoura (2023) describes the back-propagation algorithm in terms of an alternative formulation called the F-adjoint method. In particular, by the F-adjoint algorithm the computation of the loss gradient, with respect…

Machine Learning · Computer Science 2024-07-17 Ahmed Boughammoura

This paper presents a groundbreaking advancement in the theory of operators defined on octonionic Hilbert spaces, successfully resolving a fundamental challenge that has persisted for over six decades. Due to the intrinsic non-associative…

Functional Analysis · Mathematics 2025-12-05 Qinghai Huo , Guangbin Ren , Irene Sabadini
‹ Prev 1 2 3 10 Next ›