A Limitation of V-Matrix based Methods
This highlights a theoretical flaw in V-matrix methods, which is incremental as it points out an existing issue rather than proposing a new solution.
The paper identifies a limitation in V-matrix based methods for conditional probability estimation, showing that the constrained quadratic optimization problem may not always have a consistent solution due to inconsistent inequality constraints.
To estimate the conditional probability functions based on the direct problem setting, V-matrix based method was proposed. We construct V-matrix based constrained quadratic programming problems for which the inequality constraints are inconsistent. In particular, we would like to present that the constrained quadratic optimization problem for conditional probability estimation using V-matrix method may not have a consistent solution always.