Trimmed Density Ratio Estimation
This addresses robustness issues in density ratio estimation for machine learning and statistical applications, but appears incremental as it builds on existing methods with a trimming approach.
The paper tackles the problem of density ratio estimation being vulnerable to corrupted data points by proposing a robust estimator that automatically identifies and trims outliers, with analysis of parameter estimation error in high-dimensional settings and experimental verification.
Density ratio estimation is a vital tool in both machine learning and statistical community. However, due to the unbounded nature of density ratio, the estimation procedure can be vulnerable to corrupted data points, which often pushes the estimated ratio toward infinity. In this paper, we present a robust estimator which automatically identifies and trims outliers. The proposed estimator has a convex formulation, and the global optimum can be obtained via subgradient descent. We analyze the parameter estimation error of this estimator under high-dimensional settings. Experiments are conducted to verify the effectiveness of the estimator.