Multi-Target XGBoostLSS Regression
This work addresses a limitation in gradient boosting for practitioners dealing with dependent multi-target regression, though it is incremental as it builds on an existing probabilistic framework.
The paper tackles the problem of modeling dependencies between multiple targets in regression tasks by extending XGBoostLSS to handle multivariate settings, resulting in improved runtime and competitive accuracy compared to existing gradient boosting methods.
Current implementations of Gradient Boosting Machines are mostly designed for single-target regression tasks and commonly assume independence between responses when used in multivariate settings. As such, these models are not well suited if non-negligible dependencies exist between targets. To overcome this limitation, we present an extension of XGBoostLSS that models multiple targets and their dependencies in a probabilistic regression setting. Empirical results show that our approach outperforms existing GBMs with respect to runtime and compares well in terms of accuracy.