Relative Density-Ratio Estimation for Robust Distribution Comparison
نویسندگان
چکیده
Divergence estimators based on direct approximation of density ratios without going through separate approximation of numerator and denominator densities have been successfully applied to machine learning tasks that involve distribution comparison such as outlier detection, transfer learning, and two-sample homogeneity test. However, since density-ratio functions often possess high fluctuation, divergence estimation is a challenging task in practice. In this letter, we use relative divergences for distribution comparison, which involves approximation of relative density ratios. Since relative density ratios are always smoother than corresponding ordinary density ratios, our proposed method is favorable in terms of nonparametric convergence speed. Furthermore, we show that the proposed divergence estimator has asymptotic variance independent of the model complexity under a parametric setup, implying that the proposed estimator hardly overfits even with complex models. Through experiments, we demonstrate the usefulness of the proposed approach.
منابع مشابه
Gas-liquid Relative Permeability Estimation in 2D Porous Media by Lattice Boltzmann Method: Low Viscosity Ratio 2D LBM Relative Permeability
This work is a primary achievement in studying the CO2 and N2–oil systems. To predict gas-liquid relative permeability curves, a Shan-Chen type multicomponent multiphase lattice Boltzmann model for two-phase flow through 2D porous media is developed. Periodic and bounce back boundary conditions are applied to the model with the Guo scheme for the external body force (i.e.,...
متن کاملRobust Estimation in Linear Regression Model: the Density Power Divergence Approach
The minimum density power divergence method provides a robust estimate in the face of a situation where the dataset includes a number of outlier data. In this study, we introduce and use a robust minimum density power divergence estimator to estimate the parameters of the linear regression model and then with some numerical examples of linear regression model, we show the robustness of this est...
متن کاملNoise spectrum estimation using Gaussian mixture model-based speech presence probability for robust speech recognition
This work presents a noise spectrum estimator based on the Gaussian mixture model (GMM)-based speech presence probability (SPP) for robust speech recognition. Estimated noise spectrum is then used to compute a subband a posteriori signal-to-noise ratio (SNR). A sigmoid shape weighting rule is formed based on this subband a posteriori SNR to enhance the speech spectrum in the auditory domain, wh...
متن کاملThe Effect of Station Density and Regional Division on Spatial Distribution of Daily Rainfall
Rainfall is one of the most important climatic variables in the hydrology cycle. In flood estimation as well as environmental pollution studies in medium to large watersheds not only mus temporal pattern of rainfall t be known, but also the knowledge of its spatial distribution is required. Estimation of daily rainfall distribution without comparison and selection of 
suitable methods may le...
متن کاملThe Effect of Station Density and Regional Division on Spatial Distribution of Daily Rainfall
Rainfall is one of the most important climatic variables in the hydrology cycle. In flood estimation as well as environmental pollution studies in medium to large watersheds not only mus temporal pattern of rainfall t be known, but also the knowledge of its spatial distribution is required. Estimation of daily rainfall distribution without comparison and selection of suitable methods may lead...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neural computation
دوره 25 5 شماره
صفحات -
تاریخ انتشار 2011