Results 31 to 40 of about 51,558 (305)
Sets of convergence of exponential series [PDF]
THEOREM. Let { a, } denote a sequence of numbers contained in the interval [0, 27r] and dense in a subinterval of length q for some positive number r. Let J(q) denote the set of integers which are divisible by [27r/fl] where the symbol [x ] denotes the largest positive integer not greater than x.
openaire +1 more source
Exponential convergence on fixed points.
Exponential convergence on fixed points.
Dongsuk Kang (12501389) +2 more
core +1 more source
Bayesian Optimization with Exponential Convergence
In NIPS 2015 (Advances in Neural Information Processing Systems 2015)
Kawaguchi, Kenji +2 more
openaire +3 more sources
The exponential convergence of the CR Yamabe flow [PDF]
In this paper, we study the CR Yamabe flow with zero CR Yamabe invariant. We use the CR Poincaré inequality and a Gagliardo-Nirenberg type interpolation inequality to show that this flow has long time solution and the solution converges to a contact form with flat pseudo-Hermitian scalar curvature exponentially.
Sheng, Weimin, Wang, Kunbo
openaire +3 more sources
Convergence of exponentiated gradient algorithms
This paper studies three related algorithms: the (traditional) gradient descent (GD) algorithm, the exponentiated gradient algorithm with positive and negative weights (EG/spl plusmn/ algorithm), and the exponentiated gradient algorithm with unnormalized positive and negative weights (EGU/spl plusmn/ algorithm).
Hill, Simon, Williamson, Robert
openaire +1 more source
On rates of convergence for posterior distributions in infinite-dimensional models [PDF]
This paper introduces a new approach to the study of rates of convergence for posterior distributions. It is a natural extension of a recent approach to the study of Bayesian consistency.
WALKER S. G +5 more
core +1 more source
A Randomized Kaczmarz Algorithm with Exponential Convergence [PDF]
The Kaczmarz method for solving linear systems of equations is an iterative algorithm that has found many applications ranging from computer tomography to digital signal processing. Despite the popularity of this method, useful theoretical estimates for its rate of convergence are still scarce.
Strohmer, Thomas, Vershynin, Roman
openaire +4 more sources
Almost sure and moment exponential stability in the numerical simulation of stochastic differential equations [PDF]
Relatively little is known about the ability of numerical methods for stochastic differential equations (SDEs) to reproduce almost sure and small-moment stability.
Yuan, C. +4 more
core +1 more source
A Case of Exponential Convergence Rates for SVM
Classification is often the first problem described in introductory machine learning classes. Generalization guarantees of classification have historically been offered by Vapnik-Chervonenkis theory. Yet those guarantees are based on intractable algorithms, which has led to the theory of surrogate methods in classification.
Cabannes V., Vigogna S.
openaire +4 more sources
About the convergence rate Hermite – Pade approximants of exponential functions [PDF]
This paper studies uniform convergence rate of Hermite\,--\,Pad\'e approximants (simultaneous Pad\'e approximants) $\{\pi^j_{n,\overrightarrow{m}}(z)\}_{j=1}^k$ for a system of exponential functions $\{e^{\lambda_jz}\}_{j=1}^k ...
Starovoitov, Alexander Pavlovich +1 more
doaj +1 more source

