Constructive quantization: approximation by empirical measures
نویسندگان
چکیده
In this article, we study the approximation of a probability measure μ on R by its empirical measure μ̂N interpreted as a random quantization. As error criterion we consider an averaged p-th moment Wasserstein metric. In the case where 2p < d, we establish fine upper and lower bounds for the error, a high-resolution formula. Moreover, we provide a universal estimate based on moments, a Pierce type estimate. In particular, we show that quantization by empirical measures is of optimal order under weak assumptions.
منابع مشابه
On the Mean Speed of Convergence of Empirical and Occupation Measures in Wasserstein Distance
In this work, we provide non-asymptotic bounds for the average speed of convergence of the empirical measure in the law of large numbers, in Wasserstein distance. We also consider occupation measures of ergodic Markov chains. One motivation is the approximation of a probability measure by nitely supported measures (the quantization problem). It is found that rates for empirical or occupation me...
متن کاملDetection of perturbed quantization (PQ) steganography based on empirical matrix
Perturbed Quantization (PQ) steganography scheme is almost undetectable with the current steganalysis methods. We present a new steganalysis method for detection of this data hiding algorithm. We show that the PQ method distorts the dependencies of DCT coefficient values; especially changes much lower than significant bit planes. For steganalysis of PQ, we propose features extraction from the e...
متن کاملOn Hausdorff’s moment problem in higher dimensions
Denote by μn = ∫ x n1 1 . . . x nd d dμ(x) the n’th moment of a Borel probability measure μ on the unit cube I = [0, 1] in R. Generalizing results of Hausdorff, Hildebrandt and Schoenberg, we give a sufficient condition in terms of moments, that μ is absolutely continuous with respect to a second Borel measure ν on I. We also review a constructive approximation of measures by atomic measures us...
متن کاملA Constructive Sharp Approach to Functional Quantization of Stochastic Processes
We present a constructive approach to the functional quantization problem of stochastic processes, with an emphasis on Gaussian processes. The approach is constructive, since we reduce the infinite-dimensional functional quantization problem to a finite-dimensional quantization problem that can be solved numerically. Our approach achieves the sharp rate of the minimal quantization error and can...
متن کاملDiscriminant Pattern Recognition Using Transformation-Invariant Neurons
To overcome the problem of invariant pattern recognition, Simard, LeCun, and Denker (1993) proposed a successful nearest-neighbor approach based on tangent distance, attaining state-of-the-art accuracy. Since this approach needs great computational and memory effort, Hastie, Simard, and Säckinger (1995) proposed an algorithm (HSS) based on singular value decomposition (SVD), for the generation ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012