CEC-MMR: Cross-Entropy Clustering Approach to Multi-Modal Regression
This addresses a specific limitation in regression analysis for applications with multi-modal data, offering an incremental improvement over existing methods.
The paper tackles the problem of multi-modal regression where traditional methods like Mixture Density Networks (MDNs) struggle to accurately determine the number of components, by introducing CEC-MMR based on Cross-Entropy Clustering to automatically detect components and uniquely identify them, resulting in superior outcomes compared to classical MDNs.
In practical applications of regression analysis, it is not uncommon to encounter a multitude of values for each attribute. In such a situation, the univariate distribution, which is typically Gaussian, is suboptimal because the mean may be situated between modes, resulting in a predicted value that differs significantly from the actual data. Consequently, to address this issue, a mixture distribution with parameters learned by a neural network, known as a Mixture Density Network (MDN), is typically employed. However, this approach has an important inherent limitation, in that it is not feasible to ascertain the precise number of components with a reasonable degree of accuracy. In this paper, we introduce CEC-MMR, a novel approach based on Cross-Entropy Clustering (CEC), which allows for the automatic detection of the number of components in a regression problem. Furthermore, given an attribute and its value, our method is capable of uniquely identifying it with the underlying component. The experimental results demonstrate that CEC-MMR yields superior outcomes compared to classical MDNs.