Results 41 to 50 of about 14,949,583 (325)
Convergence Rates for Markov Chains [PDF]
SIAM Review, 1995 Summary: This is an expository paper that presents various ideas related to nonasymptotic rates of convergence for Markov chains. Such rates are of great importance for stochastic algorithms that are widely used in statistics and in computer science. They also have applications to analysis of card shuffling and other areas.
openaire +2 more sources
Rate of Convergence Towards Hartree Dynamics
, 2011 We consider a system of N bosons interacting through a two-body potential with, possibly, Coulomb-type singularities. We show that the difference between the many-body Schr\"odinger evolution in the mean-field regime and the effective nonlinear Hartree ...
A. Elgart +14 more
core +1 more source
Convergence Rate of Euler–Maruyama Scheme for SDEs with Hölder–Dini Continuous Drifts
Journal of theoretical probability, 2018 In this paper, we are concerned with convergence rate of Euler–Maruyama scheme for stochastic differential equations with Hölder–Dini continuous drifts. The key contributions are as follows: (i) by means of regularity of non-degenerate Kolmogrov equation,
J. Bao, Xing Huang, C. Yuan
semanticscholar +1 more source
Convergence Rate of Distributed ADMM Over Networks [PDF]
IEEE Transactions on Automatic Control, 2016 We propose a new distributed algorithm based on alternating direction method of multipliers (ADMM) to minimize sum of locally known convex functions using communication over a network. This optimization problem emerges in many applications in distributed
A. Makhdoumi, A. Ozdaglar
semanticscholar +1 more source
On Convergence Rate of MRetrace
MathematicsOff-policy is a key setting for reinforcement learning algorithms. In recent years, the stability of off-policy learning for value-based reinforcement learning has been guaranteed even when combined with linear function approximation and bootstrapping ...
Xingguo Chen +4 more
doaj +1 more source
Global Convergence Rate of Proximal Incremental Aggregated Gradient Methods [PDF]
SIAM Journal on Optimization, 2016 We focus on the problem of minimizing the sum of smooth component functions (where the sum is strongly convex) and a non-smooth convex function, which arises in regularized empirical risk minimization in machine learning and distributed constrained ...
N. D. Vanli +2 more
semanticscholar +1 more source
Convergence Rates for Generalized Descents [PDF]
The Electronic Journal of Combinatorics, 2011 d-descents are permutation statistics that generalize the notions of descents and inversions. It is known that the distribution of d-descents of permutations of length n satisfies a central limit theorem as n goes to infinity. We provide an explicit formula for the mean and variance of these statistics and obtain bounds on the rate of convergence using
openaire +2 more sources
Persistence in real exchange rate convergence [PDF]
Studies in Nonlinear Dynamics and Econometrics, 2014 AbstractIn this paper we use a long memory framework to examine the validity of the Purchasing Power Parity (PPP) hypothesis using both monthly and quarterly data for a panel of 47 countries over a 50 year period (1957–2009). The analysis focuses on the long memory parameter d that allows us to obtain different convergence classifications depending on ...
Thanasis Stengos, M. Ege Yazgan
openaire +2 more sources
Statistical (T) rates of convergence
Glasnik Matematicki, 2004 A real lower triangular matrix \(T\) having nonnegative elements \( t(i,j)\) for which \(\{\sum t(i,j) \mid 0 N( \varepsilon )\) may of course be said to converge to \( L \). The convergence condition may be relaxed by stipulating that the points of exception to the inequality relationship should be sparse. \( K(x,L,\varepsilon| i) \) is the set of \(
Miller, H. I., Orhan, C.
openaire +3 more sources
Convergence rate of the data-independent P-greedy algorithm in kernel-based approximation [PDF]
, 2016 Kernel-based methods provide flexible and accurate algorithms for the reconstruction of functions from meshless samples. A major question in the use of such methods is the influence of the samples locations on the behavior of the approximation, and ...
G. Santin, B. Haasdonk
semanticscholar +1 more source