𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Rates of Convergence of Adaptive Step-Size of Stochastic Approximation Algorithms

✍ Scribed by S. Shao; Percy P.C. Yip

Publisher
Elsevier Science
Year
2000
Tongue
English
Weight
115 KB
Volume
244
Category
Article
ISSN
0022-247X

No coin nor oath required. For personal study only.

πŸ“œ SIMILAR VOLUMES

Convergence Rates of Regularized Approxi
Convergence Rates of Regularized Approximation Processes
✍ Sen-Yen Shaw; Hsiang Liu πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 185 KB

We define the concept of an A-regularized approximation process and prove for it uniform convergence theorems and strong convergence theorems with optimal and non-optimal rates. The sharpness of non-optimal convergence is also established. The general results provide a unified approach to dealing wi

Adaptive weak approximation of stochasti
Adaptive weak approximation of stochastic differential equations
✍ Anders Szepessy; RaΓΊl Tempone; Georgios E. Zouraris πŸ“‚ Article πŸ“… 2001 πŸ› John Wiley and Sons 🌐 English βš– 320 KB

## Abstract Adaptive time‐stepping methods based on the Monte Carlo Euler method for weak approximation of ItΓ΄ stochastic differential equations are developed. The main result is new expansions of the computational error, with computable leading‐order term in a posteriori form, based on stochastic

Convergence of discretized stochastic (i
Convergence of discretized stochastic (interest rate) processes with stochastic drift term
✍ Deelstra, G. ;Delbaen, F. πŸ“‚ Article πŸ“… 1998 πŸ› John Wiley and Sons 🌐 English βš– 118 KB

For applications in finance, we study the stochastic differential equation dX ) dB Q with a negative real number, g a continuous function vanishing at zero which satisfies a Ho¨lder condition and a measurable and adapted stochastic process such that R S du( R a.e. for all t31> and which may have a

Exponential convergence of products of r
Exponential convergence of products of random matrices: Application to adaptive algorithms
✍ George V. Moustakides πŸ“‚ Article πŸ“… 1998 πŸ› John Wiley and Sons 🌐 English βš– 164 KB πŸ‘ 1 views

We introduce a novel methodology for analysing well known classes of adaptive algorithms. Combining recent developments concerning geometric ergodicity of stationary Markov processes and long existing results from the theory of Perturbations of Linear Operators we first study the behaviour and conve