We follow the method of Section 2.3.2.
Let be a set of independent uniform-distributed RV in
Let be an -by- full-rank matrix and let
be the feature vector
Saddlepoint Approximation for Linear Function of Uniformly-Distributed Data
is uniformly distributed, the CGF is given by
For conciseness, define
From these expressions, we may find the saddle-point (2.12).