Universal compression of Gaussian sources with unknown parameters
نویسندگان
چکیده
For a collection of distributions over a countable support set, the worst case universal compression formulation by Shtarkov attempts to assign a universal distribution over the support set. The formulation aims to ensure that the universal distribution does not underestimate the probability of any element in the support set relative to distributions in the collection. When the alphabet is uncountable and we have a collection P of Lebesgue continuous measures instead, we ask if there is a corresponding universal probability density function (pdf) that does not underestimate the value of the density function at any point in the support relative to pdfs in P . An example of such a measure class is the set of all Gaussian distributions whose mean and variance are in a specified range. We quantify the formulation in the uncountable support case with the attenuation of the class—a quantity analogous to the worst case redundancy of a collection of distributions over a countable alphabet. An attenuation of A implies that the worst case optimal universal pdf at any point x in the support is always at least the value any pdf in the collection P assigns to x divided by A. We analyze the attenuation of the worst optimal universal pdf over length-n samples generated i.i.d. from a Gaussian distribution whose mean can be anywhere between −α/2 to α/2 and variance between σ m and σ M . We show that this attenuation is finite, grows with the number of samples as O(n), and also specify the attentuation exactly without approximations. When only one parameter is allowed to vary, we show that the attenuation grows as O(√n), again keeping in line with results from prior literature that fix the order of magnitude as a factor of √ n per parameter. In addition, we also specify the attenuation exactly without approximation when only the mean or only the variance is allowed to vary.
منابع مشابه
Universal Incremental Slepian-Wolf Coding
We present a strategy for Slepian-Wolf coding when the joint distribution of the sources is unknown. The encoders use an incremental transmission policy, and the decoder a universal sequential decision test. We show that the decoder is able to decode shortly after the rates of transmission exceed the Slepian-Wolf bounds. The decoder then send an ACK back to the encoders, terminating transmissio...
متن کاملAdaptive Signal Detection in Auto-Regressive Interference with Gaussian Spectrum
A detector for the case of a radar target with known Doppler and unknown complex amplitude in complex Gaussian noise with unknown parameters has been derived. The detector assumes that the noise is an Auto-Regressive (AR) process with Gaussian autocorrelation function which is a suitable model for ground clutter in most scenarios involving airborne radars. The detector estimates the unknown...
متن کاملUniversal noiseless coding
A&ruct-Universal coding is any asymptotically opt imum method of block-to-block memoryless source coding for sources with unknown parameters. This paper considers noiseless coding for such sources, primarily in terms of variable-length coding, with performance measured as a function of the coding redundancy relative to the per-letter conditional source entropy given the unknown parameter. It is...
متن کاملA progressive universal noiseless coder
AbstructWe combine pruned tree-structured vector quantization (pruned TSVQ) with Itoh’s universal noiseless coder. By combining pruned TSVQ with universal noiseless coding, we benefit from the “successive approximation” capabilities of TSVQ, thereby allowing progressive transmission of images, while retaining the ability to noiselessly encode images of unknown statistics in a provably asymptoti...
متن کاملReconstructing Gaussian sources by spatial sampling
Consider a Gaussian memoryless multiple source with m components with joint probability distribution known only to lie in a given class of distributions. A subset of k ≤ m components are sampled and compressed with the objective of reconstructing all the m components within a specified level of distortion under a meansquared error criterion. In Bayesian and nonBayesian settings, the notion of u...
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:
- CoRR
دوره abs/1410.4550 شماره
صفحات -
تاریخ انتشار 2014