Online Learning over a Decentralized Network Through ADMM

Xu, Haipeng; Ling, Qing; Ribeiro, Alejandro

doi:10.1007/s40305-015-0104-0

Cited by 14 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these works require a central node for the dual variable updates. Other works employ the consensus ADMM variant without a central node [111] with other notable applications in target tracking [3], signal estimation [16], task assignment [112], motion planning [5], online learning [113], and parameter estimation in global navigation satellite systems [114]. Further applications of C-ADMM arise in trajectory tracking problems involving teams of robots using non-linear model predictive control [115] and in cooperative localization [116].…”

Section: Applications Of C-admmmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Distributed Optimization Methods for Multi-Robot Systems

Halsted¹,

Shorinwa²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Distributed optimization consists of multiple computation nodes working together to minimize a common objective function through local computation iterations and networkconstrained communication steps. In the context of robotics, distributed optimization algorithms can enable multi-robot systems to accomplish tasks in the absence of centralized coordination. We present a general framework for applying distributed optimization as a module in a robotics pipeline. We survey several classes of distributed optimization algorithms and assess their practical suitability for multi-robot applications. We further compare the performance of different classes of algorithms in simulations for three prototypical multi-robot problem scenarios. The Consensus Alternating Direction Method of Multipliers (C-ADMM) emerges as a particularly attractive and versatile distributed optimization method for multi-robot systems.

show abstract

Section: Applications Of C-admmmentioning

confidence: 99%

“…Applications of SOVA include collaborative manipulation [117]. C-ADMM is adapted for online learning problems with streaming data in [113].…”

Section: Applications Of C-admmmentioning

confidence: 99%

A Survey of Distributed Optimization Methods for Multi-Robot Systems

Halsted¹,

Shorinwa²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…where η is the penalty factor and the term η 2 (E nm,t−1 −E nm ) 2 is appended to make the results close to previous value E nm,t−1 in order to speed up the convergence process [33], [34].…”

Section: Real-time P2p Electricity Market Mechanismmentioning

confidence: 99%

Online Optimization for Real-Time Peer-to-Peer Electricity Market Mechanisms

Guo

Chen

Yang

et al. 2021

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

show abstract

“…Decentralized online learning. Online learning in a decentralized network has been studied in [Shahrampour and Jadbabaie, 2018, Kamp et al, 2014, Koppel et al, 2018, Zhang et al, 2018a, 2017b, Xu et al, 2015, Akbari et al, 2017, Lee et al, 2016, Nedić et al, 2015, Lee et al, 2018, Benczúr et al, 2018 1 n is the number of nodes or users and T is the total number of iterations. The regret of an online algorithm is O √ T for convex loss functions [Hazan, 2016, Shalev-Shwartz, 2012.…”

Section: Related Workmentioning

confidence: 99%

“…Decentralized online learning receives extensive attentions in recent years [Shahrampour and Jadbabaie, 2018, Kamp et al, 2014, Koppel et al, 2018, Zhang et al, 2018a, 2017b, Xu et al, 2015, Akbari et al, 2017, Lee et al, 2016, Nedić et al, 2015, Lee et al, 2018, Benczúr et al, 2018, Yan et al, 2013. It assumes that computational nodes in a network can communicate between neighbors to minimize an overall cumulative regret.…”

Section: Introductionmentioning

confidence: 99%

Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend

Zhao¹,

Zhao²,

Tang³

et al. 2019

Preprint

View full text Add to dashboard Cite

Decentralized Online Learning (online learning in decentralized networks) attracts more and more attention, since it is believed that Decentralized Online Learning can help the data providers cooperatively better solve their online problems without sharing their private data to a third party or other providers. Typically, the cooperation is achieved by letting the data providers exchange their models between neighbors, e.g., recommendation model. However, the best regret bound for a decentralized online learning algorithm is O n √ T , where n is the number of nodes (or users) and T is the number of iterations. This is clearly insignificant since this bound can be achieved without any communication in the networks. This reminds us to ask a fundamental question: Can people really get benefit from the decentralized online learning by exchanging information? In this paper, we studied when and why the communication can help the decentralized online learning to reduce the regret. Specifically, each loss function is characterized by two components: the adversarial component and the stochastic component. Under this characterization, we show that decentralized online gradient (DOG) enjoys a regret bound O √ n 2 T G 2 + nT σ 2 , where G measures the magnitude of the adversarial component in the private data (or equivalently the local loss function) and σ measures the randomness within the private data. This regret suggests that people can get benefits from the randomness in the private data by exchanging private information. Another important contribution of this paper is to consider the dynamic regret -a more practical regret to track users' interest dynamics. Empirical studies are also conducted to validate our analysis.

show abstract

Online Learning over a Decentralized Network Through ADMM

Cited by 14 publications

References 18 publications

A Survey of Distributed Optimization Methods for Multi-Robot Systems

A Survey of Distributed Optimization Methods for Multi-Robot Systems

Online Optimization for Real-Time Peer-to-Peer Electricity Market Mechanisms

Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend

Contact Info

Product

Resources

About