Implement a greedy version of Kernel Inducing Points

[db091756]

PR Type

• Feature
• Tests

Description

Adds coresubset algorithm implementing a greedy version of the KIP algorithm from https://arxiv.org/pdf/2011.00050.
Refactors inverse.py to be least_squares.py to be more generally useful.

How Has This Been Tested?

Adds corresponding unit tests.

Does this PR introduce a breaking change?

(Write your answer here.)

Screenshots

(Write your answer here.)

Checklist before requesting a review

• I have made sure that my PR is not a duplicate.
• My code follows the style guidelines of this project.
• I have commented my code, particularly in hard-to-understand areas.
• I have performed a self-review of my code.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• Any dependent changes have been merged and published in downstream modules.

[rg936672]

Looks good, just a couple of other minor documentation fixes. There's also the matter of whether to pass the intermediate state as a parameter, or whether to keep it internal - I currently think it should be a private member of GreedyKernelInducingPoints, but I'm open to have my mind changed if there's something I've overlooked!