activity
20202026
collaborators

6 papers

math.PR2026

Uniform-in-time Gaussian fluctuations for multiscale nonlinear stochastic systems via Malliavin Calculus

Shivam Singh Dhama

We establish a uniform-in-time quantitative central limit theorem (QCLT) for a nonlinear slow-fast stochastic system. We identify significant weaker sufficient conditions that enab…

math.PR2026

Quantitative Fluctuation Analysis for Continuous-Time Stochastic Gradient Descent via Malliavin Calculus

Solesne Bourguin, Shivam Singh Dhama, Konstantinos Spiliopoulos

In this paper, we establish a Quantitative Central Limit Theorem (QCLT) for the Stochastic Gradient Descent in Continuous Time (SGDCT) algorithm, whose parameter updates are govern…

math.PR2024

Uniform-in-time bounds for a stochastic hybrid system with fast periodic sampling and small white-noise

Shivam Singh Dhama, Konstantinos Spiliopoulos

We study the asymptotic behavior, uniform-in-time, of a non-linear dynamical system under the combined effects of fast periodic sampling with period and small white noise of si…

math.PR2022

Asymptotic analysis of dynamical systems driven by Poisson random measures with periodic sampling

Shivam Singh Dhama

In this article, we study the dynamics of a nonlinear system governed by an ordinary differential equation under the combined influence of fast periodic sampling with period an…

math.PR2022

Fluctuation analysis for a class of nonlinear systems with fast periodic sampling and small state-dependent white noise

Shivam Dhama, Chetan D. Pahlajani

We consider a nonlinear differential equation under the combined influence of small state-dependent Brownian perturbations of size , and fast periodic sampling with pe…

math.PR2020

Approximation of linear controlled dynamical systems with small random noise and fast periodic sampling

Shivam Dhama, Chetan D. Pahlajani

In this paper, we study the dynamics of a linear control system with given state feedback control law in the presence of fast periodic sampling at temporal frequency ($0 < δ\…