\magnification=1200
\baselineskip=20pt
\nopagenumbers
\font\big=cmr12 scaled \magstep2

\centerline{\bf STANFORD UNIVERSITY}
\centerline{\bf DEPARTMENT OF STATISTICS}
\centerline{\big DEPARTMENTAL SEMINAR}
\bigskip

\baselineskip=12pt
\centerline{4:15 p.m., Tuesday, April 11, 2000}
\centerline{Sequoia Hall Rm. 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Oleg Lepski}
\centerline{\sl Universite de Provence}
\centerline{\sl Marseille}
\bigskip
\centerline{\bf On estimation of composite functions}
\bigskip

In White Gaussian Model we are interested to estimate the function
$G:R^d\to R, d\geq 2,$  that is represented as $G=g(f)$. Here $f:R^d\to R$
and $g:R\to R$ are supposed to be smooth. We discuss some results about the
rate of convergence for the estimation of $G$ in dependance on the
smoothness of $g$ and $f$.

\bye