Skip to content
This repository was archived by the owner on Jan 12, 2024. It is now read-only.
This repository was archived by the owner on Jan 12, 2024. It is now read-only.

MachineLearning.EstimateClassificationProbability and EstimateClassificationProbabilities needlessly divide tolerance by model size #283

Open
@abacabadabacaba

Description

@abacabadabacaba

The functions EstimateClassificationProbability and EstimateClassificationProbabilities in Microsoft.Quantum.MachineLearning namespace divide the passed tolerance by model size. There are multiple problems with this:

  • Firstly, doing this is unnecessary. It is possible to bound the probability error in terms of encoding error, and this bound doesn't depend on model size. To put it in simple terms, longer models are no more sensitive to encoding errors, so this division makes no sense.
  • When using EstimateClassificationProbabilities, the division is done twice: once in EstimateClassificationProbabilities and once more in EstimateClassificationProbability.
  • Thanks to Fix #261. #274, EstimateClassificationProbabilities now handles the special case of model length being 0. Unfortunately, EstimateClassificationProbability still doesn't handle this case properly.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Pkg-QMLIssue relates to the Microsoft.Quantum.MachineLearning package.

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions