English
Related papers

Related papers: When Does Dynamic Preconditioning Preserve the Pol…

200 papers

Numerous theories of learning propose to prevent the gradient from exponential growth with depth or time, to stabilize and improve training. Typically, these analyses are conducted on feed-forward fully-connected neural networks or simple…

Machine Learning · Computer Science 2024-01-08 Luca Herranz-Celotti , Jean Rouat

In this paper, we consider a non-linear fourth-order evolution equation of Cahn-Hilliard-type on evolving surfaces with prescribed velocity, where the non-linear terms are only assumed to have locally Lipschitz derivatives. High-order…

Numerical Analysis · Mathematics 2022-03-07 Cedric Aaron Beschle , Balázs Kovács

We study a stabilization problem of linear uncertain systems with parametric uncertainties via feedback control over data-rate-constrained channels. The objective is to find the limitation on the amount of information that must be conveyed…

Systems and Control · Computer Science 2014-05-26 Kunihisa Okano , Hideaki Ishii

Stochastic Gradient Descent (SGD) is widely used in machine learning problems to efficiently perform empirical risk minimization, yet, in practice, SGD is known to stall before reaching the actual minimizer of the empirical risk. SGD…

Machine Learning · Statistics 2017-02-09 Vivak Patel

Multiple analytical and empirical stability criteria have been derived in the literature for two planet systems. But, the dependence of the stability limit on the initial mutual inclination between the inner and outer orbits is not well…

Earth and Planetary Astrophysics · Physics 2024-04-12 Hareesh Gautham Bhaskar , Hagai Perets

We revisited the central limit theorem (CLT) for stochastic gradient descent (SGD) type methods, including the vanilla SGD, momentum SGD and Nesterov accelerated SGD methods with constant or vanishing damping parameters. By taking advantage…

Optimization and Control · Mathematics 2023-06-12 Tiejun Li , Tiannan Xiao , Guoguo Yang

We analyze the fluctuations of incomplete $U$-statistics over a triangular array of independent random variables. We give criteria for a Central Limit Theorem (CLT, for short) to hold in the sense that we prove that an appropriately scaled…

Probability · Mathematics 2020-03-24 Matthias Löwe , Sara Terveer

In this work, we study online convex optimization with a fixed constraint function $g : \mathbb{R}^d \rightarrow \mathbb{R}$. Prior work on this problem has shown $O(\sqrt{T})$ regret and cumulative constraint satisfaction $\sum_{t=1}^{T}…

Machine Learning · Computer Science 2025-07-16 Spencer Hutchinson , Mahnoosh Alizadeh

Using a new strategy, we extend the classical Nekhoroshev's estimates to the case of H\"older regular steep near-integrable hamiltonian systems, the stability times being polynomially long in the inverse of the size of the perturbation. We…

Dynamical Systems · Mathematics 2022-09-05 Santiago Barbieri , Jean-Pierre Marco , Jessica Elisa Massetti

Regularization is a core component of modern inverse problems, as it helps establish the well-posedness of the solution of interest. Popular regularization approaches include variational regularization and iterative regularization. The…

Optimization and Control · Mathematics 2025-08-08 Jie Gao , Cesare Molinari , Silvia Villa , Jingwei Liang

Higher-order time integration methods that unconditionally preserve the positivity and linear invariants of the underlying differential equation system cannot belong to the class of general linear methods. This poses a major challenge for…

Numerical Analysis · Mathematics 2022-02-24 Thomas Izgin , Stefan Kopecz , Andreas Meister

Non-normal transient growth of disturbances is considered as an essential prerequisite for subcritical transition in shear flows, i.e. transition to turbulence despite linear stability of the laminar flow. In this work we present numerical…

Fluid Dynamics · Physics 2014-03-06 Simon Maretzke , Björn Hof , Marc Avila

We consider the fluctuation of linear eigenvalue statistics of random band $n\times n$ matrices whose entries have the form $\mathcal{M}_{ij}=b^{-1/2}u^{1/2}(|i-j|)\tilde w_{ij}$ with i.i.d. $w_{ij}$ possessing the $(4+\varepsilon)$th…

Mathematical Physics · Physics 2015-09-30 Mariya Shcherbina

The Allen-Cahn equation is a fundamental model for phase transitions, offering critical insights into the dynamics of interface evolution in various physical systems. This paper investigates the stability and robustness of frequently…

Numerical Analysis · Mathematics 2025-04-11 Wenrui Hao , Sun Lee , Xiaofeng Xu , Zhiliang Xu

In this paper, the stability of $\theta$-methods for delay differential equations is studied based on the test equation $y'(t)=-A y(t) + B y(t-\tau)$, where $\tau$ is a constant delay and $A$ is a positive definite matrix. It is mainly…

Numerical Analysis · Mathematics 2023-11-29 Alejandro Rodríguez-Fernández , Jesús Martín-Vaquero

Often in the analysis of first-order methods for both smooth and nonsmooth optimization, assuming the existence of a growth/error bound or KL condition facilitates much stronger convergence analysis. Hence separate analysis is typically…

Optimization and Control · Mathematics 2023-01-10 Benjamin Grimmer

We investigate the stability of katabatic slope flows over an infinitely wide and uniformly cooled planar surface subject to an additional forcing due to a uniform downslope wind field aloft. We adopt an extension of Prandtl's original…

Fluid Dynamics · Physics 2020-02-19 Cheng-Nian Xiao , Inanc Senocak

Softmax feedback systems are a common mathematical core of entropy-regularized reinforcement learning, logit game dynamics, population choice, and mean-field variational updates. Their central stability question is simple: when does a…

Machine Learning · Computer Science 2026-05-18 Tongxi Wang

We present a new approach, inspired by Stein's method, to prove a central limit theorem (CLT) for linear statistics of $\beta$-ensembles in the one-cut regime. Compared with the previous proofs, our result requires less regularity on the…

Probability · Mathematics 2019-02-20 Gaultier Lambert , Michel Ledoux , Christian Webb

Classical discrete-time adaptive controllers provide asymptotic stabilization and tracking; neither exponential stabilization nor a bounded noise gain is typically proven. In recent work it has been shown, in both the pole placement…

Optimization and Control · Mathematics 2019-02-26 Daniel E Miller , Mohamad T. Shahab
‹ Prev 1 4 5 6 7 8 10 Next ›