Blackbox and derivative-free optimization: theory, algorithms and applications

62 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Beyond Sparsity: Tree Regularization of Deep Models for Interpretability (2017, background): “While one could resort to derivativefree optimization techniques (Audet and Kokkolaras 2016), gradient descent has been an extremely fast and robust way of training networks (Goodfellow, Bengio, and Courville 2016).”
A Survey of Optimization Methods From a Machine Learning Perspective (2019, methodology): “on may not exist or is not easy to calculate. The solution of ﬁnding the optimal point, in this case, is called derivative-free optimization, which is a discipline of mathematical optimization [155], [156], [157]. It can ﬁnd the optimal solution without the gradient information. There are mainly two”
Improving the Interpretability of Deep Neural Networks with Knowledge Distillation (2018, methodology): “They measure human simulatability as the average decision path length and make the decision tree loss differentiable by adopting the technique of derivative-free optimization techniques [46].”