Lower Bounds for the Gibbs Sampler over Mixtures of Gaussians
نویسندگان
چکیده
Inferring the parameters of a mixture model based on observed data is a classical problem in machine learning that has received much attention from computer scientists and statisticians alike. One of the first computational approaches to this problem was given by Dempster, Laird, and Rubin (1977) in the form of the popular EM algorithm. The goal of their algorithm was to find the parameters which maximized the likelihood of the observed data. While their algorithm is only guaranteed to converge to a local maximum (Wu, 1983), others have demonstrated efficient algorithms that recover the true parameters of mixtures of various distributions (Moitra & Valiant, 2010; Belkin & Sinha, 2010; Hsu & Kakade, 2013).
منابع مشابه
Mixing Rates for the Gibbs Sampler over Restricted Boltzmann Machines
The mixing rate of a Markov chain (Xt)t=0 is the minimum number of steps before the distribution of Xt is close to its stationary distribution with respect to total variation distance. In this work, we give upper and lower bounds for the mixing rate of the Gibbs sampler over Restricted Boltzmann Machines.
متن کاملThe Infinite Mixture of Infinite Gaussian Mixtures
Dirichlet process mixture of Gaussians (DPMG) has been used in the literature for clustering and density estimation problems. However, many real-world data exhibit cluster distributions that cannot be captured by a single Gaussian. Modeling such data sets by DPMG creates several extraneous clusters even when clusters are relatively well-defined. Herein, we present the infinite mixture of infini...
متن کاملThe Infinite Mixture of Infinite Gaussian Mixtures
Dirichlet process mixture of Gaussians (DPMG) has been used in the literature for clustering and density estimation problems. However, many real-world data exhibit cluster distributions that cannot be captured by a single Gaussian. Modeling such data sets by DPMG creates several extraneous clusters even when clusters are relatively well-defined. Herein, we present the infinite mixture of infini...
متن کاملA note on convergence rates of Gibbs sampling for nonparametric mixtures∗
We present a mathematical analysis of a class of Gibbs sampler algorithms for nonparametric mixtures, which use Dirichlet process priors and have updating steps which are partially discrete and partially continuous. We prove that such Gibbs samplers are uniformly ergodic, and we give a quantitative bound on their convergence rate. In a special case we can give a much sharper quantitative bound;...
متن کاملApplication of Electrochemistry to Determination of Transfer Gibbs Energies and Autoprotolysis Constants for Aqueous Mixtures of Dimethyl Sulfoxide
A practical potentiometric method was applied successfully to experimental electrochemical data in order to determine the autoprotolysis constants (pKap) of water + dimethyl sulfoxide mixtures containing 0-90 % of DMSO by volume at 25° C and 0.1 M ionic strength was maintained in each mixture by NaClO4 solution. The results indicated that water-DMSO mixtures are more basic media than pure water...
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 2014