Abstract
In [1] Carr established propagation error bounds for a particular Runge-Kutta (RK) procedure, and suggested that similar bounds could be established for other RK procedures obtained by choosing the parameters differently.
- 1 J. W. CARR III, Error bounds for the Runge-Kutta single-step integration process. J. Assoc. Comp. Mach. 5, 39-44 (1958). Google Scholar
Index Terms
- A Generalization of a Theorem of Carr on Error Bounds for Rung-Kutta Procedures
Recommendations
Strengthened Information-theoretic Bounds on the Generalization Error
2019 IEEE International Symposium on Information Theory (ISIT)The following problem is considered: given a joint distribution P<inf>XY</inf> and an event E, bound P<inf>XY</inf> (E) in terms of P<inf>X</inf>P<inf>Y</inf> (E) (where P<inf>X</inf>P<inf>Y</inf> is the product of the marginals of P<inf>XY</inf>) and a ...
Generalization bounds for uniformly stable algorithms
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsUniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002). Specifically, for a loss function with range bounded in [0,...
Error Bounds for the Runge-Kutta Single-Step Integration Process
Although numerous writers have stated that the class of single-step (“Runge-Kutta”—like) methods of numerical integration of ordinary differential equations are stable under calculational or round-off error, no one has given formal equations for the ...
Comments