LS-SVR as a Bayesian RBF network
This work provides a formal connection between LS-SVR and Bayesian methods, potentially enabling improvements in LS-SVR by leveraging Bayesian techniques, though it is incremental as it builds on prior observations of similarities.
The paper demonstrates theoretical similarities between Least Squares Support Vector Regression (LS-SVR) with an RBF kernel and maximum a posteriori inference on Bayesian RBF networks, showing they are equivalent under a specific Gaussian prior, and validates this with computational experiments on standard regression benchmarks.
We show theoretical similarities between the Least Squares Support Vector Regression (LS-SVR) model with a Radial Basis Functions (RBF) kernel and maximum a posteriori (MAP) inference on Bayesian RBF networks with a specific Gaussian prior on the regression weights. Although previous works have pointed out similar expressions between those learning approaches, we explicit and formally state the existing correspondences. We empirically demonstrate our result by performing computational experiments with standard regression benchmarks. Our findings open a range of possibilities to improve LS-SVR by borrowing strength from well-established developments in Bayesian methodology.