Suchergebnisse - Doubly stochastic gradient algorithm

New Scalable and Efficient Online Pairwise Learning Algorithm von Gu, Bin, Bao, Runxue, Zhang, Chenkang, Huang, Heng

“… To address this challenging problem, in this article, we propose a dynamic doubly stochastic gradient algorithm (D2SG …”
Volltext

Pseudo-gradient algorithm for identification of doubly stochastic cylindrical image model von Krasheninnikov, Victor, Kuvayskova, Yuliya, Subbotin, Alexey

“… The peculiarity of the domain for specifying such images requires its consideration in their models and processing algorithms …”
Volltext

Accelerated Doubly Stochastic Gradient Algorithm for Large-scale Empirical Risk Minimization von Shen, Zebang, Qian, Hui, Mu, Tongzhou, Zhang, Chao

“… In this paper, we propose a doubly stochastic algorithm with a novel accelerating multi-momentum technique to solve large scale empirical risk minimization problem for learning tasks …”
Volltext

Faster doubly stochastic functional gradient by gradient preconditioning for scalable kernel methods von Zhang, Zhuan, Zhou, Shuisheng, Yang, Ting, Zhang, Junna

“… The doubly stochastic functional gradient descent algorithm (DSG) that is memory friendly and computationally efficient can effectively scale up kernel methods …”
Volltext

Scalable Kernel Ordinal Regression via Doubly Stochastic Gradients von Gu, Bin, Geng, Xiang, Li, Xiang, Shi, Wanli, Zheng, Guansheng, Deng, Cheng, Huang, Heng

“… Doubly stochastic gradient (DSG) is a very efficient and scalable kernel learning algorithm that combines random feature approximation with stochastic functional optimization …”
Volltext

A new large-scale learning algorithm for generalized additive models von Gu, Bin, Zhang, Chenkang, Huo, Zhouyuan, Huang, Heng

“… After that, we propose a wrapper algorithm to optimize the generalized additive models. Importantly, we introduce a doubly stochastic gradient algorithm (DSG …”
Volltext

Stochastic gradient descent for hybrid quantum-classical optimization von Sweke, Ryan, Wilde, Frederik, Meyer, Johannes, Schuld, Maria, Faehrmann, Paul K., Meynard-Piganeau, Barthélémy, Eisert, Jens

“… Within the context of hybrid quantum-classical optimization, gradient descent based optimizers typically require the evaluation of expectation values with respect to the outcome of parameterized quantum circuits …”
Volltext

Asynchronous Parallel Large-Scale Gaussian Process Regression von Dang, Zhiyuan, Gu, Bin, Deng, Cheng, Huang, Heng

“… To address this challenging problem, in this article, we propose an asynchronous doubly stochastic gradient algorithm to handle the large-scale training of GPR …”
Volltext

Gradient-free method for distributed multi-agent optimization via push-sum algorithms von Yuan, Deming, Xu, Shengyuan, Lu, Junwei

“… ‐doubly stochastic matrix. We present a distributed method that employs gradient‐free oracles and push …”
Volltext

Block-Randomized Stochastic Proximal Gradient for Low-Rank Tensor Factorization von Fu, Xiao, Ibrahim, Shahana, Wai, Hoi-To, Gao, Cheng, Huang, Kejun

“… However, existing stochastic CPD algorithms are not flexible to incorporate a variety of constraints/regularization terms that are of interest in signal and data analytics …”
Volltext

Accelerated Doubly Stochastic Gradient Descent for Tensor CP Decomposition von Wang, Qingsong, Cui, Chunfeng, Han, Deren

“… In this paper, we focus on the acceleration of doubly stochastic gradient descent method for computing the CANDECOMP/PARAFAC (CP …”
Volltext

Randomized Gradient-Free Distributed Optimization Methods for a Multiagent System With Unknown Cost Function von Pang, Yipeng, Hu, Guoqiang

“… as compared with the doubly stochastic weighting matrix. Without the true gradient information, we establish asymptotic convergence to the approximated …”
Volltext

Distributed Push-Sum Algorithm for Multi-Agent optimization Via One-Point Gradient Estimator von Wang, Cong, Yuan, Deming, Zhang, Baoyong

“… We propose an efficient distributed optimization algorithm that is based on push-sum algorithm and one-point gradient estimator, which removes the needs for doubly stochastic weight matrix …”
Volltext

Push-Sum Distributed Online Optimization With Bandit Feedback von Wang, Cong, Xu, Shengyuan, Yuan, Deming, Zhang, Baoyong, Zhang, Zhengqiang

“… online convex optimization algorithm that achieves sublinear individual regret for every node is developed …”
Volltext

The identification of doubly stochastic circular image model von Krasheninnikov, Victor, Malenova, Olga, Subbotin, Alexey

“… In the present paper, autoregressive models of circular images are considered. To represent heterogeneous images with random heterogeneities, «doubly stochastic» models are used in which one or more images control the parameters of the resulting image. Pseudo-gradient algorithms for the modal identification are proposed. The conducted statistical modeling showed that these algorithms give good model identification …”
Volltext

Block-wise primal-dual algorithms for large-scale doubly penalized ANOVA modeling von Fu, Penghui, Tan, Zhiqiang

“… To facilitate large-scale training of DPAM using backfitting or block minimization, two suitable primal-dual algorithms are developed, including both batch and stochastic versions, for updating each …”
Volltext

Approximate Bayesian model inversion for PDEs with heterogeneous and state-dependent coefficients von Barajas-Solano, D.A., Tartakovsky, A.M.

“… We present two approximate Bayesian inference methods for parameter estimation in partial differential equation (PDE) models with space-dependent and …”
Volltext

Learning Deep Generative Models With Doubly Stochastic Gradient MCMC von Du, Chao, Zhu, Jun, Zhang, Bo

“… We present doubly stochastic gradient MCMC, a simple and generic method for (approximate) Bayesian inference of DGMs in a collapsed continuous parameter space …”
Volltext

High-Dimensional Nonconvex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation von Mokhtari, Aryan, Koppel, Alec

“… We propose a Doubly Stochastic Successive Convex approximation scheme (DSSC) able to handle non-convex regularized expected risk minimization …”
Volltext

On the Use of the Doubly Stochastic Matrix Models for the Quadratic Assignment Problem von Santucci, Valentino, Ceberio, Josu

“… In this paper, we consider the Quadratic Assignment Problem (QAP) as a case study, and propose using Doubly Stochastic Matrices (DSMs …”
Weitere Angaben