Metraipolis › archive › dc_eb61e269a464
Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates — arXiv:2608.27612
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27612
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:24:50.129Z
- SHA-256 of the archived text
fe48aea364c28a088a22ad6352be5e0371add50ec54c8f98e1a94a30d2fa8a1a- Stable URL of this page
https://metraipolis.com/documento/dc_eb61e269a464
How to cite
Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates — arXiv:2608.27612 — arXiv (en), https://arxiv.org/abs/2608.27612 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb61e269a464 (Metraipolis archive dc_eb61e269a464, sha256 fe48aea364c28a088a22ad6352be5e0371add50ec54c8f98e1a94a30d2fa8a1a)
BibTeX
@misc{dceb61e269a464,
title = {Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates — arXiv:2608.27612},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27612},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb61e269a464; sha256 fe48aea364c28a088a22ad6352be5e0371add50ec54c8f98e1a94a30d2fa8a1a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27612. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In neuroevolution, indirect encoding generates neural network connectivity from a compact genome rather than specifying each connection. ES-HyperNEAT automatically discovers where to place hidden nodes by examining CPPN output patterns: it recursively subdivides space using a quadtree, expanding regions where CPPN outputs show high variance. This adaptive approach discovers network topology without manual substrate specification, extending the fixed-grid HyperNEAT framework built on NEAT. However, the quadtree resists tensorization. Each depth level depends on the parent's variance, forcing sequential evaluation. Different CPPNs produce different subdivision patterns, preventing batching. And variable leaf counts are incompatible with JAX's static shape requirement for JIT compilation. Our prior work confirmed these limits at depths exceeding 5, and a JAX reimplementation of the quadtree yielded only marginal speedup despite batched optimizations, motivating the eager reformulation presented here. We present EMR-HyperNEAT, which evaluates all positions at all resolutions up front, then filters using the same variance criterion: ES-HyperNEAT's subdivide_if(var > $\theta$) becomes eval_all(); filter(var > $\theta$). This performs more CPPN queries than necessary, but all queries become independent and parallelizable across both cores and population members, reducing complexity from \BigO($4^D$) to \BigO($4^D/P$) across $P$ parallel cores. Recurrent substrate configurations become feasible through a connection type taxonomy. The experiments section validates 12-34$\times$ on-device GPU speedup on XOR at depths 5-7, and empirically higher solve rates across benchmarks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI). Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.27612 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T07:00:16.268Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).