Zobrazeno 1 - 10
of 279
pro vyhledávání: '"Proske, Frank"'
We study a linear filtering problem where the signal and observation processes are described as solutions of linear stochastic differential equations driven by time-space Brownian sheets. We derive a stochastic integral equation for the conditional v
Externí odkaz:
http://arxiv.org/abs/2407.06386
In this paper, we consider a McKean-Vlasov (mean-field) stochastic partial differential equations (SPDEs) driven by a Brownian sheet. We study the propagation of chaos for a space-time Ornstein-Uhlenbeck SPDE type. Subsequently, we prove the existenc
Externí odkaz:
http://arxiv.org/abs/2404.19490
Autor:
Compagnoni, Enea Monzio, Orvieto, Antonio, Kersting, Hans, Proske, Frank Norbert, Lucchi, Aurelien
Minimax optimization problems have attracted a lot of attention over the past few years, with applications ranging from economics to machine learning. While advanced optimization methods exist for such problems, characterizing their dynamics in stoch
Externí odkaz:
http://arxiv.org/abs/2402.12508
In this paper we study a Pontryagin type stochastic maximum principle for the optimal control of a system, where the state dynamics satisfy a stochastic partial differential equation (SPDE) driven by a two-parameter (time-space) Brownian motion (also
Externí odkaz:
http://arxiv.org/abs/2308.00173
We prove the existence of a unique Malliavin differentiable strong solution to a stochastic differential equation on the plane with merely integrable coefficients driven by the fractional Brownian sheet with Hurst parameter $H=(H_1,H_2)\in(0,\frac{1}
Externí odkaz:
http://arxiv.org/abs/2307.09086
Autor:
Compagnoni, Enea Monzio, Biggio, Luca, Orvieto, Antonio, Proske, Frank Norbert, Kersting, Hans, Lucchi, Aurelien
We study the SAM (Sharpness-Aware Minimization) optimizer which has recently attracted a lot of interest due to its increased performance over more classical variants of stochastic gradient descent. Our main contribution is the derivation of continuo
Externí odkaz:
http://arxiv.org/abs/2301.08203
In this paper we are interested in a quasi-linear hyperbolic stochastic differential equation (HSPDE) when the vector field is merely bounded and measurable. Although the deterministic counterpart of such equation may be ill-posed (in the sense that
Externí odkaz:
http://arxiv.org/abs/2212.08466
Publikováno v:
Neurips 2022
Studying the properties of stochastic noise to optimize complex non-convex functions has been an active area of research in the field of machine learning. Prior work has shown that the noise of stochastic gradient descent improves optimization by ove
Externí odkaz:
http://arxiv.org/abs/2209.09162
The $d$-dimensional Ornstein--Uhlenbeck process (OUP) describes the trajectory of a particle in a $d$-dimensional, spherically symmetric, quadratic potential. The OUP is composed of a drift term weighted by a constant $\theta \geq 0$ and a diffusion
Externí odkaz:
http://arxiv.org/abs/2208.04029
We deduce stability and pathwise uniqueness for a McKean-Vlasov equation with random coefficients and a multidimensional Brownian motion as driver. Our analysis focuses on a non-Lipschitz drift coefficient and includes moment estimates for random It\
Externí odkaz:
http://arxiv.org/abs/2205.02176