11 citations · 18 across the 6 of their papers we have counts for
6 papers
Universal Approximation in Dropout Neural Networks
Oxana A. Manita, Mark A. Peletier, Jacobus W. Portegies +2
We prove two universal approximation theorems for a range of dropout neural networks. These are feed-forward neural networks in which each edge is given a random -valued f…
On convergence of 1D Markov diffusions to heavy-tailed invariant density
O. A. Manita, A. Yu. Veretennikov
Rate of convergence is studied for a diffusion process on the half line with a non-sticky reflection to a heavy-tailed 1D invariant distribution which density on the half line has…
Positivity of transition probabilities of infinite-dimensional diffusion processes on ellipsoids
Oxana Manita
We consider diffusion processes in Hilbert spaces with constant non-degenerate diffusion operators and show that, under broad assumptions on the drift, the transition probabilities…
Estimates for Kantorovich functionals between solutions to Fokker -- Planck -- Kolmogorov equations with dissipative drifts
Oxana Manita
We obtain estimates for the Kantorovich functionals between solutions to different Fokker -- Planck -- Kolmogorov equations for measures with same diffusion part but different drif…
On uniqueness of solutions to nonlinear Fokker--Planck--Kolmogorov equations
Oxana A. Manita, Maxim S. Romanov, Stanislav V. Shaposhnikov
We study uniqueness of flows of probability measures solving the Cauchy problem for nonlinear Fokker-Planck-Kolmogorov equation with unbounded coefficients. Sufficient conditions f…
On the well-posedness of the Cauchy problem for Fokker--Planck--Kolmogorov equations with potential terms on arbitrary domains
Oxana A. Manita, Stanislav V. Shaposhnikov
We study the Cauchy problem for Fokker--Planck--Kolmogorov equations with unbounded and degenerate coefficients. Sufficient conditions for the existence and uniqueness of solutions…