… the coverage function of a random set, which is a possibility measure. In this paper, we show
that a histogram is the coverage function of a determined random set. This suggests other …

… The random histogram proposed in this paper can be viewed as an extended version of
such bloom filter. We not only record whether each bucket is empty, but also keep a count for …

… In this section we review the definition of an equi-height histogram and approximate
histograms. We show that using the standard error metrics for approximate histograms can be …

… Analogous to random Fourier feature maps to approximate shift-invariant kernels, such as
the Gaussian kernel, on Rd, we develop a new randomized technique called random Laplace …

… the breakpoints are randomly shifted. We introduce thus a random breakpoints histogram
(RH-… We compare our algorithm to Average Shifted Histogram (ASH) and to several classic …

… -based histograms that use random … histograms that are built on the full data. On the other
hand, as we shall see in Section 6, the wavelet-based histograms (whether they use random …

… interval valued set statistics collected … histograms. We first introduce the basics of mathematical
possibility theory in terms of fuzzy measures, random set and evidence theory, fuzzy sets, …

… of histogram if the event is the act of measurement of a random value … histogram is the
purpose of independent measurement of the random value with gradual filling up of the histogram, …

… are set to ‘1’ while other bins are set to ‘0’ (eg if the histograms are projected into a 10-d
space and if k = 4, we will obtain 10-bit histogram … As an alternative to random projections, we …

… In this section, we experimentally study the effectiveness of onedimensional ST-histograms
for a wide range of data skew (z) using random workloads and the procedure outlined in …