Results 31 to 40 of about 13,863,967 (339)
Decentralized Proximal Gradient Algorithms With Linear Convergence Rates [PDF]
IEEE Transactions on Automatic Control, 2019 This article studies a class of nonsmooth decentralized multiagent optimization problems where the agents aim at minimizing a sum of local strongly-convex smooth components plus a common nonsmooth term.
Sulaiman A. Alghunaim +3 more
semanticscholar +1 more source
Convergence Aspects of Some Robust Estimators Based Upon Prefiltering of the Input-Output Data [PDF]
Modeling, Identification and Control, 1990 By prefiltering the input/output data and employing certain decentralized estimation techniques, it is possible to improve the robustness of some estimators significantly.
Rolf Henriksen, Erik Weyer
doaj +1 more source
Rate of Convergence for Cardy’s Formula [PDF]
Communications in Mathematical Physics, 2014 We show that crossing probabilities in 2D critical site percolation on the triangular lattice in a piecewise analytic Jordan domain converge with power law rate in the mesh size to their limit given by the Cardy-Smirnov formula. We use this result to obtain new upper and lower bounds of exp(O(sqrt(log log R))) R^(-1/3) for the probability that the ...
Nachmias, Asaf +2 more
openaire +3 more sources
A note on the convergence rates in precise asymptotics
Journal of Inequalities and Applications, 2019 Let {X,Xn,n≥1} $\{X, X_{n}, n\geq1\}$ be a sequence of i.i.d. random variables with EX=0 $EX=0$, EX2=σ2 $EX^{2}=\sigma^{2}$. Set Sn=∑k=1nXk $S_{n}=\sum_{k=1}^{n}X_{k}$ and let N ${\mathcal {N} }$ be the standard normal random variable. Let g(x) $g(x)$ be
Yong Zhang
doaj +1 more source
Geometric Estimation of Multivariate Dependency
Entropy, 2019 This paper proposes a geometric estimator of dependency between a pair of multivariate random variables. The proposed estimator of dependency is based on a randomly permuted geometric graph (the minimal spanning tree) over the two multivariate samples ...
Salimeh Yasaei Sekeh, Alfred O. Hero
doaj +1 more source
Fast convergence rates of deep neural networks for classification [PDF]
Neural Networks, 2018 We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss.
Yongdai Kim, Ilsang Ohn, Dongha Kim
semanticscholar +1 more source
A unified approach for regularizing discretized linear ill‐posed problems
Mathematical Modelling and Analysis, 2009 In this paper we deal with regularization approaches for discretized linear ill‐posed problems in Hilbert spaces. As opposite to other contributions concerning this topic the smoothness of the unknown solution is measured with so‐called approximative ...
Torsten Hein
doaj +1 more source
Convergence Rates of Subseries [PDF]
The American Mathematical Monthly, 2019 Let $(x_n)$ be a positive real sequence decreasing to $0$ such that the series $\sum_n x_n$ is divergent and $\liminf_{n} x_{n+1}/x_n>1/2$. We show that there exists a constant $θ\in (0,1)$ such that, for each $\ell>0$, there is a subsequence $(x_{n_k})$ for which $\sum_k x_{n_k}=\ell$ and $x_{n_k}=O(θ^k)$.
openaire +2 more sources
On rates of convergence for posterior distributions in infinite-dimensional models [PDF]
, 2007 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
Convergence rates of variational posterior distributions [PDF]
Annals of Statistics, 2017 We study convergence rates of variational posterior distributions for nonparametric and high-dimensional inference. We formulate general conditions on prior, likelihood, and variational class that characterize the convergence rates.
Fengshuo Zhang, Chao Gao
semanticscholar +1 more source