Available benchmarks
Note
Some benchmarks are briefly described in the list below. For a complete
list of benchmarks, see GitHub repositories of the form benchopt/benchmark_*.
Notation: In what follows, (or n_samples
) stands for the number of samples and (or n_features
) stands for the number of features.
where
where is the pinball loss:
Given some data assumed to be linearly
related to unknown independent sources with
where is also unknown, the objective of
linear ICA is to recover up to permutation and scaling of its columns.
The objective in this benchmark is related to some estimation on
quantified with the so-called AMARI distance.
Given n square symmetric positive matrices , it consists of solving
the following problem:
where stands for the matrix determinant and stands
for the operator that keeps only the diagonal elements of a matrix. Optionally, the
matrix can be enforced to be orthogonal.
See benchmark_* repositories on GitHub for more.