A collection of optimizers for complex optimization problems.
Optimizers are integrated into the existing Optimization node, you can find them in the dropdown.

We offer three types of solutions:

  • Gradient-based: for convex optimization.
  • Gradient-free: for complex design domains.
  • Metamodeling: when the objective function is expensive to calculate, we fit a simpler model to inform the next samples.

Gradient-based optimizers

NLOpt optimizer family. These include local and global optimizers.

Gradient-free optimizers

Genetic Algorithms

Metamodel optimizers

  • Gaussian Processes
  • Polynomial Chaos Expansion
  • Deep Neural Network

Try it here!

Dense Neural Network surrogate model optimizer
Dense Neural Network surrogate model optimizer