Zobrazeno 1 - 10
of 766
pro vyhledávání: '"Friedlander, Michael P."'
Autor:
Fan, Zhenan, Zhou, Zirui, Pei, Jian, Friedlander, Michael P., Hu, Jiajie, Li, Chengliang, Zhang, Yong
Federated learning is an emerging technique for training models from decentralized data sets. In many applications, data owners participating in the federated learning system hold not only the data but also a set of domain knowledge. Such knowledge i
Externí odkaz:
http://arxiv.org/abs/2208.07530
We study the federated optimization problem from a dual perspective and propose a new algorithm termed federated dual coordinate descent (FedDCD), which is based on a type of coordinate descent method developed by Necora et al.[Journal of Optimizatio
Externí odkaz:
http://arxiv.org/abs/2201.11183
Federated learning is a popular technology for training machine learning models on distributed data sources without sharing data. Vertical federated learning or feature-based federated learning applies to the cases that different data sources share t
Externí odkaz:
http://arxiv.org/abs/2201.02658
Autor:
Fan, Zhenan, Fang, Huang, Zhou, Zirui, Pei, Jian, Friedlander, Michael P., Liu, Changxin, Zhang, Yong
Publikováno v:
2022 IEEE 38th International Conference on Data Engineering (ICDE)
Federated learning is an emerging decentralized machine learning scheme that allows multiple data owners to work collaboratively while ensuring data privacy. The success of federated learning depends largely on the participation of data owners. To su
Externí odkaz:
http://arxiv.org/abs/2109.09046
A memory-efficient framework is described for the cardinality-constrained structured data-fitting problem. Dual-based atom-identification rules are proposed that reveal the structure of the optimal primal solution from near-optimal dual solutions. Th
Externí odkaz:
http://arxiv.org/abs/2107.11373
The projection onto the epigraph or a level set of a closed proper convex function can be achieved by finding a root of a scalar equation that involves the proximal operator as a function of the proximal parameter. This paper develops the variational
Externí odkaz:
http://arxiv.org/abs/2102.06809
The Binary Iterative Hard Thresholding (BIHT) algorithm is a popular reconstruction method for one-bit compressed sensing due to its simplicity and fast empirical convergence. There have been several works about BIHT but a theoretical understanding o
Externí odkaz:
http://arxiv.org/abs/2012.12886
The signal demixing problem seeks to separate a superposition of multiple signals into its constituent components. This paper studies a two-stage approach that first decompresses and subsequently deconvolves the noisy and undersampled observations of
Externí odkaz:
http://arxiv.org/abs/2010.10508
Online mirror descent (OMD) and dual averaging (DA) -- two fundamental algorithms for online convex optimization -- are known to have very similar (and sometimes identical) performance guarantees when used with a fixed learning rate. Under dynamic le
Externí odkaz:
http://arxiv.org/abs/2006.02585
We consider the problem of finding a low rank symmetric matrix satisfying a system of linear equations, as appears in phase retrieval. In particular, we solve the gauge dual formulation, but use a fast approximation of the spectral computations to ac
Externí odkaz:
http://arxiv.org/abs/2006.01014