Probabilistic estimation while ignoring outliers
ثبت نشده
چکیده
Logistic regression learns a parameterized mapping from feature vectors to probability vectors and is for example central to estimating click rates for ads on web pages. The parameter is found by minimizing the logistic loss. However minimizing any convex loss summed over a set of examples is prone to outliers. We define a versatile method for designing non-convex losses that ameliorate the effect of outliers while avoiding local minima experimentally.
منابع مشابه
Simultaneous robust estimation of multi-response surfaces in the presence of outliers
A robust approach should be considered when estimating regression coefficients in multi-response problems. Many models are derived from the least squares method. Because the presence of outlier data is unavoidable in most real cases and because the least squares method is sensitive to these types of points, robust regression approaches appear to be a more reliable and suitable method for addres...
متن کاملA Generic Approach for Robust Probabilistic Estimation with Graphical Models
Probabilistic estimation using graphical models plays an important role in today’s intelligent and autonomous systems. This paper summarizes our work on robust probabilistic estimation using such models. This robustness, i.e. the algorithmic fault-tolerance in the presence of outliers is crucial for any autonomous system aiming at long-term operation. We show how probabilistic estimation using ...
متن کاملIdentification of outliers types in multivariate time series using genetic algorithm
Multivariate time series data, often, modeled using vector autoregressive moving average (VARMA) model. But presence of outliers can violates the stationary assumption and may lead to wrong modeling, biased estimation of parameters and inaccurate prediction. Thus, detection of these points and how to deal properly with them, especially in relation to modeling and parameter estimation of VARMA m...
متن کاملApplying Point Estimation and Monte Carlo Simulation Methods in Solving Probabilistic Optimal Power Flow Considering Renewable Energy Uncertainties
The increasing penetration of renewable energy results in changing the traditional power system planning and operation tools. As the generated power by the renewable energy resources are probabilistically changed, the certain power system analysis tolls cannot be applied in this case. Probabilistic optimal power flow is one of the most useful tools regarding the power system analysis in presen...
متن کاملRobust Probabilistic Multivariate Calibration Model
In this paper we propose a robust probabilistic multivariate calibration (RPMC) model in an attempt to identify linear relationships between two sets of observed variables contaminated with outliers. Instead of the Gaussian assumptions that predominate in classical statistical models, RPMC is closely related with the multivariate Student's t-distribution over noises and latent variables. As a r...
متن کامل