Niching Methods and Multimodal Optimization Performance

By Mike Preuss. 2015

22 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Optimization & Training, Signal Processing

How researchers see this paper

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

In Artificial Intelligence

1. Frank Hutter
2. Ilya Loshchilov
3. Quoc V. Le
4. B. Qu
5. Caitong Yue
6. Jing J. Liang
7. Dan Hendrycks
8. Xuanyi Dong

In Optimization & Training

1. Frank Hutter
2. Ilya Loshchilov
3. Ronghang Hu
4. Dan Hendrycks
5. B. Qu
6. Caitong Yue
7. Jing J. Liang
8. Quoc V. Le

In Signal Processing

1. Frank Hutter
2. Ilya Loshchilov
3. B. Qu
4. Caitong Yue
5. Jing J. Liang

Citations in the corpus

• SGDR: Stochastic Gradient Descent with Warm Restarts (2016, methodology): “Gradient-free optimization approaches based on niching methods (Preuss, 2015) usually can deal with this task by covering the search space with dynamically allocated niches of local optimizers.”
• A Multiobjective Particle Swarm Optimizer Using Ring Topology for Solving Multimodal Multiobjective Problems (2018, methodology): “A most popular method to solve multimodal problems is niching technique [6] inspired on the way organisms evolve in nature.”
• SGDR: Stochastic Gradient Descent with Restarts (2016, methodology): “Gradient-free optimization approaches based on niching methods (Preuss, 2015) usually can deal with this task by covering the search space with dynamically allocated niches of local optimizers.”