# Quantum Machine Learning Algorithm Approximations

**URL:** <https://discuss.pennylane.ai/t/quantum-machine-learning-algorithm-approximations/5052>\
**Category:** PennyLane Help\
**Created:** [August 15, 2024, 8:25am UTC](https://discuss.pennylane.ai/t/quantum-machine-learning-algorithm-approximations/5052 "2024-08-15T08:25:04Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![kevinkawchak](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/kevinkawchak/32/1801_2.png) [@kevinkawchak](https://discuss.pennylane.ai/u/kevinkawchak)\
**Post date:** [August 15, 2024, 8:25am UTC](https://discuss.pennylane.ai/t/quantum-machine-learning-algorithm-approximations/5052/1 "2024-08-15T08:25:04Z")

</div>

Is there a way to approximate each QML algorithm for speed-ups?

---

<div class="post-metadata">

**Author:** ![CatalinaAlbornoz](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/catalinaalbornoz/32/1196_2.png) [@CatalinaAlbornoz](https://discuss.pennylane.ai/u/CatalinaAlbornoz)\
**Post date:** [August 16, 2024, 1:21am UTC](https://discuss.pennylane.ai/t/quantum-machine-learning-algorithm-approximations/5052/2 "2024-08-16T01:21:54Z")

</div>

Hi @kevinkawchak ,

Most QML algorithms are slower than classical ML algorithms. I encourage you to read our blog post on [benchmarking near-term quantum algorithms](https://pennylane.ai/blog/2024/03/benchmarking-near-term-quantum-algorithms-is-an-art/) where our team shows that even simple classical models are usually better than quantum ones. It aligns very well with Maria Schuld’s vision on [why measuring performance is our biggest blind spot in quantum machine learning](https://pennylane.ai/blog/2022/03/why-measuring-performance-is-our-biggest-blind-spot-in-quantum-machine-learning/). Quantum machine learning still has a lot of room for research and it probably makes sense to stop looking for speedup improvements in applications where classical methods are already good.