Distributed information-theoretic clustering

Pichler, Georg; Piantanida, Pablo; Matz, Gerald

doi:10.1093/imaiai/iaab007

Cited by 30 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through powerful machine learning algorithms, we can dig out a lot of useful information from these data. In recent years, many different clustering algorithms have been proposed [2] . As one of the key technologies to deal with big data, they have been more and more widely used in digital image processing [3] , computer science [4][5] , species category analysis [6][7] , and other fields.…”

Section: Introductionmentioning

confidence: 99%

Adaptive density peak clustering algorithm combined with sparse search

Duan

Wei

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

With the advantages of few parameters and the ability to deal with clusters of arbitrary shape, the density peak clustering algorithm has attracted wide attention since it came out. However, the algorithm has problems such as high time complexity, poor clustering effect on complex data sets, and the need to manually select cluster centers. Aiming at the above shortcomings, an improved density peak clustering algorithm is proposed. Combined with the sparse search algorithm, the calculation of the similarity between each point and its nearest neighbor is simplified, and the problem of the high time complexity of the algorithm is overcome. A new local density definition method is adopted to make the density of data points better reflect the spatial structure of data distribution and to improve the clustering accuracy of the algorithm. Finally, a strategy for automatically selecting cluster centers is proposed to improve the adaptability of the algorithm. The algorithm is used to compare with the other improved algorithm on artificial data sets and real data sets. The experimental results show that the proposed algorithm can show a better clustering effect and can quickly and accurately identify various complex clusters.

show abstract

Section: Introductionmentioning

confidence: 99%

Adaptive density peak clustering algorithm combined with sparse search

Duan

Wei

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…In particular, let

be a bivariate source characterized by a fixed joint probability law

and consider all Markov chains

. The Double-Sided Information Bottleneck (DSIB) function is defined as [ 2 ]:

where the maximization is over all

and

satisfying

and

. This problem is illustrated in Figure 1 .…”

Section: Introductionmentioning

confidence: 99%

“…An optimization algorithm was presented that intertwines both row and column clustering at all stages. Distributed clustering from a proper information-theoretic perspective was first explicitly considered by Pichler et al [ 2 ]. Consider the model illustrated in Figure 3 .…”

Section: Introductionmentioning

confidence: 99%

“…The DSIB problem addressed in our paper is, in fact, a single-letter version of the distributed clustering setup [ 2 ]. The inner bound in [ 2 ] coincides with our problem definition.…”

Section: Introductionmentioning

confidence: 99%

“…The DSIB problem addressed in our paper is, in fact, a single-letter version of the distributed clustering setup [ 2 ]. The inner bound in [ 2 ] coincides with our problem definition. Moreover, if the Markov condition

is imposed on the multi-letter variant, then those problems are equivalent.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Double-Sided Information Bottleneck Function

Dikshtein

Ordentlich

Shamai

2022

Entropy

View full text Add to dashboard Cite

A double-sided variant of the information bottleneck method is considered. Let (X,Y) be a bivariate source characterized by a joint pmf PXY. The problem is to find two independent channels PU|X and PV|Y (setting the Markovian structure U→X→Y→V), that maximize I(U;V) subject to constraints on the relevant mutual information expressions: I(U;X) and I(V;Y). For jointly Gaussian X and Y, we show that Gaussian channels are optimal in the low-SNR regime but not for general SNR. Similarly, it is shown that for a doubly symmetric binary source, binary symmetric channels are optimal when the correlation is low and are suboptimal for high correlations. We conjecture that Z and S channels are optimal when the correlation is 1 (i.e., X=Y) and provide supporting numerical evidence. Furthermore, we present a Blahut–Arimoto type alternating maximization algorithm and demonstrate its performance for a representative setting. This problem is closely related to the domain of biclustering.

show abstract

Resource allocation and congestion control in clustered M2M communication using Q‐learning

Hussain

Anpalagan

Khwaja

et al. 2016

Trans. Emerging Tel. Tech.

View full text Add to dashboard Cite

In this paper, we apply a Q‐learning algorithm to carry out slot assignment for machine type communication devices (MTCDs) in machine‐to‐machine communication. We first make use of a K‐means clustering algorithm to overcome the congestion problem in an machine‐to‐machine network where each MTCD is associated with one controller. Subsequently, we formulate the slot selection problem as an optimisation problem. Then, we present a solution using the Q‐learning algorithm to select conflict‐free slot assignment in a random access network with MTCD controllers. The performance of the solution is dependent on parameters such as learning rate and reward. We thoroughly analyse the performance of the proposed algorithm considering different parameters related to its operation. The convergence time, that is, the time required to reach a solution, decreases with increasing value of learning rate, whereas the convergence probability increases. In addition, for smaller values of learning rate, the convergence time decreases with increasing reward values. We also compare with simple ALOHA and channel‐based scheduled allocation and show that the proposed Q‐learning‐based technique has a higher probability of assigning slots compared with these techniques. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Distributed information-theoretic clustering

Cited by 30 publications

References 34 publications

Adaptive density peak clustering algorithm combined with sparse search

Adaptive density peak clustering algorithm combined with sparse search

The Double-Sided Information Bottleneck Function

Resource allocation and congestion control in clustered M2M communication using Q‐learning

Contact Info

Product

Resources

About