English
Related papers

Related papers: A regularity method for lower bounds on the Lyapun…

200 papers

We propose a new approach to non-parametric density estimation that is based on regularizing a Sobolev norm of the density. This method is statistically consistent, and makes the inductive bias of the model clear and interpretable. While…

Machine Learning · Statistics 2024-02-15 Mark Kozdoba , Binyamin Perets , Shie Mannor

We consider a rather general class of evolutionary PDEs involving dissipation (of possibly fractional order), which competes with quadratic nonlinearities on the regularity of the overall equation. This includes as prototype models,…

Analysis of PDEs · Mathematics 2015-06-16 Animikh Biswas , Eitan Tadmor

Sobolev-type regularity results are proved for solutions to a class of second order elliptic equations with a singular or degenerate weight, under non-homogeneous Neumann conditions. As an application a Pohozaev-type identity for weak…

Analysis of PDEs · Mathematics 2022-01-11 Veronica Felli , Giovanni Siclari

We study Malliavin differentiability of solutions to sub-critical singular parabolic stochastic partial differential equations (SPDEs) and we prove the existence of densities for a class of singular SPDEs. Both of these results are…

Probability · Mathematics 2018-09-12 Philipp Schönbauer

We present and prove a version of the elliptic regularity theorem for partial differential equations involving fractional Riemann-Liouville derivatives. In this case, regularity is defined in terms of Sobolev spaces $H^s(X)$: if the forcing…

Analysis of PDEs · Mathematics 2021-05-03 Arran Fernandez

We present an efficient and validated method for approximating the stationary measures of random dynamical systems with smooth additive noise. The approach leverages the strong regularizing properties of the associated transfer operator…

Dynamical Systems · Mathematics 2026-02-24 Stefano Galatolo , Charles Lopez Vereau , Luigi Marangio , Isaia Nisoli

Stochastic Gradient Descent (SGD) has become the method of choice for solving a broad range of machine learning problems. However, some of its learning properties are still not fully understood. We consider least squares learning in…

Machine Learning · Statistics 2020-06-22 Nicole Mücke , Enrico Reiss

We introduce a novel approach based on stochastic optimization to find the optimal sampling distribution for the data-driven stability analysis of switched linear systems. Our goal is to address limitations of existing approaches, in…

Optimization and Control · Mathematics 2025-09-01 Alexis Vuille , Guillaume O. Berger , Raphaël M. Jungers

In this article, relying on Foster-Lyapunov drift conditions, we establish subexponential upper and lower bounds on the rate of convergence in the $\mathrm{L}^p$-Wasserstein distance for a class of irreducible and aperiodic Markov…

Probability · Mathematics 2022-02-28 Ari Arapostathis , Guodong Pang , Nikola Sandrić

We consider the problem of finding the shortest possible period for an exactly periodic solution to some given autonomous ordinary differential equation. We show that, given a pair of Lyapunov-like observable functions defined over the…

Dynamical Systems · Mathematics 2025-10-16 Jeremy P. Parker

We present a new methodology for studying non-Hamiltonian nonlinear systems based on an information theoretic extension of a renormalization group technique using a modified maximum entropy principle. We obtain a rigorous dimensionally…

Computational Physics · Physics 2013-06-28 M. Schmuck , M. Pradas , S. Kalliadasis , G. A. Pavliotis

We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze Stochastic Differential Equations (SDEs) that model SGD either…

Machine Learning · Computer Science 2024-07-03 Adrien Schertzer , Loucas Pillaud-Vivien

The coefficients in a second order parabolic linear stochastic partial differential equation (SPDE) are estimated from multiple spatially localised measurements. Assuming that the spatial resolution tends to zero and the number of…

Statistics Theory · Mathematics 2024-07-26 Randolf Altmeyer , Anton Tiepner , Martin Wahl

This work aims to prove the small time large deviation principle (LDP) for a class of stochastic partial differential equations (SPDEs) with locally monotone coefficients in generalized variational framework. The main result could be…

Probability · Mathematics 2021-02-23 Shihu Li , Wei Liu , Yingchao Xie

This paper establishes a Freidlin-Wentzell large deviation principle for stochastic differential equations(SDEs) under locally weak monotonicity conditions and Lyapunov conditions. We illustrate the main result of the paper by showing that…

Probability · Mathematics 2021-10-14 Jian Wang , Hao Yang , Jianliang Zhai , Tusheng Zhang

We consider the Cauchy problem for a linear stochastic partial differential equation. By extending the parametrix method for PDEs whose coefficients are only measurable with respect to the time variable, we prove existence, regularity in…

Probability · Mathematics 2019-12-13 Andrea Pascucci , Antonello Pesce

Semilinear stochastic partial differential equations on bounded domains $\mathscr{D}$ are considered. The semilinear term may have arbitrary polynomial growth as long as it is continuous and monotone except perhaps near the origin. Typical…

Probability · Mathematics 2019-09-25 Neelima , David Šiška

We prove existence and up to the boundary regularity estimates in $L^{p}$ and H\"{o}lder spaces for weak solutions of the linear system $$ \delta \left( A d\omega \right) + B^{T}d\delta \left( B\omega \right) = \lambda B\omega + f \text{ in…

Analysis of PDEs · Mathematics 2025-04-02 Swarnendu Sil

The pseudo-likelihood method is one of the most popular algorithms for learning sparse binary pairwise Markov networks. In this paper, we formulate the $L_1$ regularized pseudo-likelihood problem as a sparse multiple logistic regression…

Machine Learning · Statistics 2017-04-10 Sinong Geng , Zhaobin Kuang , David Page

Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the…

Machine Learning · Statistics 2020-09-02 Gang Wang , Bingcong Li , Georgios B. Giannakis