A deep, localized random feature map with hit-and-run initialization matches or beats reservoir computing forecast skill on three chaotic benchmarks with orders of magnitude fewer parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning dynamical systems with hit-and-run random feature maps
A deep, localized random feature map with hit-and-run initialization matches or beats reservoir computing forecast skill on three chaotic benchmarks with orders of magnitude fewer parameters.