2015 IEEE International Conference on Communications (ICC) 2015
DOI: 10.1109/icc.2015.7248486
|View full text |Cite
|
Sign up to set email alerts
|

Communication theoretic prediction on networked data

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2015
2015
2020
2020

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 16 publications
0
4
0
Order By: Relevance
“…Hence, σ 2 1k δ * 1k ≤ ε, which implies |δ * 1k −δ 1k | ≤ max σij =0 {σ −2 ij }ε, for k = 0, 2. Moreover, forδ 20 where the second inequality is due to δ * 20 ≤ 1, and the third inequality is from |α 0 | ≤ ε and σ 2 10 δ * 10 ≤ ε. Finally, the verification of (38) for the restδ ij 's is the same as the previous cases.…”
Section: Appendix a Proof Of Lemmamentioning
confidence: 99%
See 1 more Smart Citation
“…Hence, σ 2 1k δ * 1k ≤ ε, which implies |δ * 1k −δ 1k | ≤ max σij =0 {σ −2 ij }ε, for k = 0, 2. Moreover, forδ 20 where the second inequality is due to δ * 20 ≤ 1, and the third inequality is from |α 0 | ≤ ε and σ 2 10 δ * 10 ≤ ε. Finally, the verification of (38) for the restδ ij 's is the same as the previous cases.…”
Section: Appendix a Proof Of Lemmamentioning
confidence: 99%
“…However, the Viterbi algorithm [10] allows us to reduce the complexity significantly. Note that (20) is equivalent to finding the path such that the inverse sum of σ 2,(k) ikik+1 is minimized.…”
Section: Multi-hop Layered Networkmentioning
confidence: 99%
“…However, the Viterbi algorithm [10] allows us to reduce the complexity significantly. Note that (20) is equivalent to finding the path such that the inverse sum of σ 2,(k) ikik+1 is minimized. Taking 1/σ 2,(k) ikik+1 as a cost, we can now apply the the Viterbi algorithm to find the path with minimal total cost, and hence the complexity is reduced to O(L).…”
Section: Remark 2 (Viterbi Algorithm)mentioning
confidence: 99%
“…It has been shown in [3] that the local geometric approach plays a crucial role in finding an investment strategy that maximizes an incremental growth rate in repeated investments [15]. The local geometric approach has also been exploited to a wide range of applications in machine learning: a learning problem in graphical models [16], an inference problem in hidden Markov models [17], [18], and big networked data analytics via communication and information theory [19], [20].…”
Section: Applications Of the Local Geometric Approachmentioning
confidence: 99%