Metraipolis › archive › dc_c035f79958ce
A Study of Hidden-State Optimization Order in Predictive Coding Networks — arXiv:2609.00686
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00686
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:33:35.929Z
- SHA-256 of the archived text
66895940c749c85ed3a96b3f24d7e0ef06459ed69ff2ed80be2d410c711cbac6- Stable URL of this page
https://metraipolis.com/documento/dc_c035f79958ce
How to cite
A Study of Hidden-State Optimization Order in Predictive Coding Networks — arXiv:2609.00686 — arXiv (en), https://arxiv.org/abs/2609.00686 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c035f79958ce (Metraipolis archive dc_c035f79958ce, sha256 66895940c749c85ed3a96b3f24d7e0ef06459ed69ff2ed80be2d410c711cbac6)
BibTeX
@misc{dcc035f79958ce,
title = {A Study of Hidden-State Optimization Order in Predictive Coding Networks — arXiv:2609.00686},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00686},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c035f79958ce; sha256 66895940c749c85ed3a96b3f24d7e0ef06459ed69ff2ed80be2d410c711cbac6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00686. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Local learning methods offer an alternative to end-to-end backpropagation, but their unstructured local objectives can produce weak feature learning in deep networks. We study whether the order of hidden-state optimization can address this limitation. We propose a boundary-first inference schedule that partitions a model into chunks, first coordinates hidden states at chunk boundaries, and then refines representations within each chunk. We instantiate this schedule in predictive coding networks (PCNs), a local-learning framework in which hidden activities and prediction errors are explicitly exposed during inference. On CIFAR-10, the resulting boundary-first predictive-coding instantiation improves accuracy over standard predictive coding by $9.77\%$ under a standard parametrization and by $5.51\%$ under a $\mu$-parametrization. Diagnostic analyses further show more non-trivial early-layer updates, lower initial-to-final CKA, and more diverse layerwise gradients, consistent with stronger feature learning. These results support boundary-first, chunk-based inference as a practical design principle for predictive-coding training and motivate its study in broader local-learning systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00686 — 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 2026-10-17T06:15:12.813Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).