Spectral Experts for Estimating Mixtures of Linear Regressions
نویسندگان
چکیده
Discriminative latent-variable models are typically learned using EM or gradient-based optimization, which suffer from local optima. In this paper, we develop a new computationally efficient and provably consistent estimator for a mixture of linear regressions, a simple instance of a discriminative latentvariable model. Our approach relies on a lowrank linear regression to recover a symmetric tensor, which can be factorized into the parameters using a tensor power method. We prove rates of convergence for our estimator and provide an empirical evaluation illustrating its strengths relative to local optimization (EM). Last Modified: June 18, 2013
منابع مشابه
Application 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 کاملMixtures of regressions with predictor-dependent mixing proportions
Abstract We extend the standard mixture of linear regressions model by allowing mixing proportions to be modeled nonparametrically as a function of the predictors. This framework allows for more flexibility in the modeling of the mixing proportions than the fully parametric mixture of experts model, which we also discuss. We present an EM-like algorithm for estimation of the new model. We also ...
متن کاملIdentifying Regression Outliers and Mixtures Graphically
Regressions in practice can include outliers and other unknown subpopulation structure. For example, mixtures of regressions occur if there is an omitted categorical predictor like gender or location and different regressions occur within each category. The theory of regression graphics based on central subspaces can be used to construct graphical solutions to long-standing problems of this typ...
متن کاملAn Overview of Nonlinear Spectral Unmixing Methods in the Processing of Hyperspectral Data
The hyperspectral imagery provides images in hundreds of spectral bands within different wavelength regions. This technology has increasingly applied in different fields of earth sciences, such as minerals exploration, environmental monitoring, agriculture, urban science, and planetary remote sensing. However, despite the ability of these data to detect surface features, the measured spectrum i...
متن کاملMixtures of Experts Estimate a Posteriori Probabilities Mixtures of Experts Estimate a Posteriori Probabilities
The mixtures of experts (ME) model ooers a modular structure suitable for a divide-and-conquer approach to pattern recognition. It has a probabilistic interpretation in terms of a mixture model, which forms the basis for the error function associated with MEs. In this paper, it is shown that for classiication problems the minimization of this ME error function leads to ME outputs estimating the...
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 2013