A Fast Algorithm for Robust Mixtures in the Presence of Measurement Errors

Abstract

Abstract-In experimental and observational sciences, detecting atypical, peculiar data from large sets of measurements has the potential of highlighting candidates of interesting new types of objects that deserve more detailed domain-specific followup study. However, measurement data is nearly never free of measurement errors. These errors can generate false outliers that are not truly interesting. Although many approaches exist for finding outliers, they have no means to tell to what extent the peculiarity is not simply due to measurement errors. To address this issue, we have developed a model-based approach to infer genuine outliers from multivariate data sets when measurement error information is available. This is based on a probabilistic mixture of hierarchical density models, in which parameter estimation is made feasible by a tree-structured variational expectationmaximization algorithm. Here, we further develop an algorithmic enhancement to address the scalability of this approach, in order to make it applicable to large data sets, via a K-dimensionaltree based partitioning of the variational posterior assignments. This creates a non-trivial tradeoff between a more detailed noise model to enhance the detection accuracy, and the coarsened posterior representation to obtain computational speedup. Hence, we conduct extensive experimental validation to study the accuracy/speed tradeoffs achievable in a variety of data conditions. We find that, at low-to-moderate error levels, a speedup factor that is at least linear in the number of data points can be achieved without significantly sacrificing the detection accuracy. The benefits of including measurement error information into the modeling is evident in all situations, and the gain roughly recovers the loss incurred by the speedup procedure in large error conditions. We analyze and discuss in detail the characteristics of our algorithm based on results obtained on appropriately designed synthetic data experiments, and we also demonstrate its working in a real application example.Index Terms-K-dimensional (KD)-tree, measurement errors, outlier detection, robust mixture modeling, variational expectation-maximization (EM) algorithm.

Simultaneous Bayesian Clustering and Feature Selection Through Student’s ${t}$ Mixtures Model

“…Tree-like structural factorization in VB has been shown to be superior over the full factorization scheme [44], [45]. The factorization can be summarized as follows:…”

Improved Graph Embedding for Robust Recognition with outliers

“…However, in data analysis, such as biomedical research, a great challenge exists, i.e., the inevitable artifacts in the signal recordings 7,8 , which are one of the major factors accounting for reduced signal quality. Artifacts can be caused by various factors such as the clinical image artifacts from illumination variations and dust particles, measurement errors in biochemistry 8 , independent scatters caused by biological tissues that are smaller than the acoustical wavelength 9 and artifacts in EEG recordings due to blinks and eye movement, a large number of spontaneous brain activities, or spikes.…”

“…Artifacts can be caused by various factors such as the clinical image artifacts from illumination variations and dust particles, measurement errors in biochemistry 8 , independent scatters caused by biological tissues that are smaller than the acoustical wavelength 9 and artifacts in EEG recordings due to blinks and eye movement, a large number of spontaneous brain activities, or spikes. Artifacts are usually characterized by several orders of magnitude larger than the signal of interest, which cannot be described by the standard Gaussian distribution.…”

“…A more favorable way is to detect the artifacts or outliers and then use approaches like regression, the blind source separation (BSS) method for artifact removal. Although some methods have been proposed to find outliers, it is difficult to determine the extent to which the peculiarities would be outliers 8 . Even if the artifacts or the outliers are located, the process of eliminating the artifact component by using BSS methods such as independent component analysis (ICA) is not trivial and may result in the loss or distortion of useful information in the extracted features 16 .…”

A multi-cycled sequential memetic computing approach for constrained optimisation

“…whereĝ i = g i , 1 ≤ i ≤ q,ĝ j = |h j | − ε, j = q + 1, · · · , m. Many machine learning 5 problems, such as image processing [69], ordinal regression [17,18], robust clustering [56,58], correlation analysis [59], and others, can be formulated as NLP.…”