A new second order Taylor-like theorem with an optimized reduced remainder

Abstract

In this paper, we derive a variant of the Taylor theorem to obtain a new minimized remainder. For a given function $f$ defined on the interval $[a,b]$, this formula is derived by introducing a linear combination of $f^{\prime }$ computed at $n+1$ equally spaced points in $[a,b]$, together with $f^{\prime \prime }(a)$ and $f^{\prime \prime }(b)$. We then consider two classical applications of this Taylor-like expansion: the interpolation error and the numerical quadrature formula. We show that using this approach improves both the Lagrange $P_2$ - interpolation error estimate and the error bound of the Simpson rule in numerical integration.