Concepts#
A run of the algorithm is configured along three independent axes: what you constrain, how wide each confidence interval is, and how those intervals are combined into a single bound. These pages cover one axis each, on top of the mathematical background they share.
Candidate selection and the safety test, delta splitting, interval arithmetic, and the predicted bound that steers the optimizer.
The five shipped fairness definitions, how to choose between them, and the base variables you write your own constraints over.
Hoeffding, empirical Bernstein, betting and Student’s t — what each assumes, and which is tighter under what conditions.
The seldonian_type variants, from uniform delta splitting to
affine-form compilation.
See also
The two axes are orthogonal: any inequality may be paired with any
seldonian_type.