# Optimizing an opaque function **URL:** \ **Category:** Supervised ML: Regression and Classification\ **Tags:** week-module-1\ **Created:** [May 27, 2023, 8:40am UTC](https://community.deeplearning.ai/t/optimizing-an-opaque-function/344714 "2023-05-27T08:40:55Z")\ **Posts on this page:** 1\ **Showing post:** 7
**Author:** ![Christian\_Simonis](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/christian_simonis/32/142583_2.png) [@Christian\_Simonis](https://community.deeplearning.ai/u/Christian_Simonis)\ **Post date:** [June 24, 2023, 5:23am UTC](https://community.deeplearning.ai/t/optimizing-an-opaque-function/344714/7 "2023-06-24T05:23:05Z")
> [@soufg](#): > > I stumbled upon the notion of “derivate free optimization” [Derivative-free optimization - Wikipedia](https://en.wikipedia.org/wiki/Derivative-free_optimization), that includes the previous answer Thanks for sharing! These threads might be interesting for you: - [Why there are so many optimizer algorithms? - #2 by Christian\_Simonis](https://community.deeplearning.ai/t/why-there-are-so-many-optimizer-algorithms/256904/2) - [Question about optimizers - #2 by Christian\_Simonis](https://community.deeplearning.ai/t/question-about-optimizers/251926/2) and also this [paper](https://arxiv.org/pdf/1206.2944.pdf) discussed [here](https://community.deeplearning.ai/t/why-there-are-so-many-optimizer-algorithms/256904/6): > [@Why there are so many optimizer algorithms?](https://community.deeplearning.ai/t/why-there-are-so-many-optimizer-algorithms/256904/6): > > Not only when gradients are difficult to compute but also if you have a highly non-convex optimization resp. if you face many local minima but many of them are not sufficient to solve your business problem, **gradient-free** methods can help, even though they can (in general) be worse performance-wise than gradient-based ones. Best regards Christian --- _[View the full topic](https://community.deeplearning.ai/t/optimizing-an-opaque-function/344714)._