STRATA
Skip to study
XLVII

IV.13 / AI

Quantum machine learning

Once data preparation and readout are counted, how does the quantum method compare with a classical baseline?

An open research question1 source references0 related experiments

Start with the question.

Quantum machine learning must be evaluated through a complete computational task, including data access and output. The HHL linear-systems algorithm is a useful starting point because its formal speedup depends on specific assumptions. Translating a quantum subroutine into a learning advantage requires checking state preparation, conditioning, measurement costs, and the strongest relevant classical comparison.

Account for every stage of a proposed speedup.

Draw a pipeline from a classical dataset to state preparation, quantum processing, measurement, and the final prediction. Assign a symbolic cost to each stage. If loading all entries already scales with dataset size, a fast internal step may not dominate the total; the diagram identifies where a claimed advantage must actually appear.

What would you inspect?

  • Input-access assumptions, condition number, desired accuracy, and number of measurements.
  • End-to-end cost compared with a classical method solving the same output task.

Take the next step.

Choose one proposed quantum learning application and write a resource table that includes both the quantum subroutine and its surrounding data operations.

Read the supporting material.

  1. Quantum Algorithm for Linear Systems of Equations

    Aram W. Harrow, Avinatan Hassidim, and Seth Lloyd · A quantum linear-systems algorithm with access, conditioning, and output assumptions.

Follow the comparisons.

Read the neighboring questions.