Analysis of the $(μ/μ_I,λ)$-$σ$-Self-Adaptation Evolution Strategy with Repair by Projection Applied to a Conically Constrained Problem
December 15, 2018 · Declared Dead · 🏛 IEEE Transactions on Evolutionary Computation
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Patrick Spettel, Hans-Georg Beyer
arXiv ID
1812.06300
Category
cs.NE: Neural & Evolutionary
Citations
2
Venue
IEEE Transactions on Evolutionary Computation
Last Checked
4 months ago
Abstract
A theoretical performance analysis of the $(μ/μ_I,λ)$-$σ$-Self-Adaptation Evolution Strategy ($σ$SA-ES) is presented considering a conically constrained problem. Infeasible offspring are repaired using projection onto the boundary of the feasibility region. Closed-form approximations are used for the one-generation progress of the evolution strategy. Approximate deterministic evolution equations are formulated for analyzing the strategy's dynamics. By iterating the evolution equations with the approximate one-generation expressions, the evolution strategy's dynamics can be predicted. The derived theoretical results are compared to experiments for assessing the approximation quality. It is shown that in the steady state the $(μ/μ_I,λ)$-$σ$SA-ES exhibits a performance as if the ES were optimizing a sphere model. Unlike the non-recombinative $(1,λ)$-ES, the parental steady state behavior does not evolve on the cone boundary but stays away from the boundary to a certain extent.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Neural & Evolutionary
🔮
🔮
The Ethereal
R.I.P.
👻
Ghosted
Deep Learning using Rectified Linear Units (ReLU)
R.I.P.
👻
Ghosted
Generative Adversarial Text to Image Synthesis
R.I.P.
👻
Ghosted
Regularized Evolution for Image Classifier Architecture Search
R.I.P.
👻
Ghosted
Temporal Ensembling for Semi-Supervised Learning
🌅
🌅
Old Age
Learning Structured Sparsity in Deep Neural Networks
Died the same way — 👻 Ghosted
R.I.P.
👻
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
👻
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
👻
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
👻
Ghosted