Metraipolis › archive › dc_19824d3eb2bb
Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence — arXiv:2609.39082
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39082
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:45:48.555Z
- SHA-256 of the archived text
d2d31b6a386744cb6c401523a6b9b4ce45fff4ade422659678249c40f34a50c0- Stable URL of this page
https://metraipolis.com/documento/dc_19824d3eb2bb
How to cite
Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence — arXiv:2609.39082 — arXiv (en), https://arxiv.org/abs/2609.39082 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_19824d3eb2bb (Metraipolis archive dc_19824d3eb2bb, sha256 d2d31b6a386744cb6c401523a6b9b4ce45fff4ade422659678249c40f34a50c0)
BibTeX
@misc{dc19824d3eb2bb,
title = {Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence — arXiv:2609.39082},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39082},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_19824d3eb2bb; sha256 d2d31b6a386744cb6c401523a6b9b4ce45fff4ade422659678249c40f34a50c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39082. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
As new evidence arrives, a sequence model must update what it remembers and how memory influences predictions. While Transformers incur computation and cache costs scaling with context length, fixed-state recurrent models offer constant-memory inference. However, linear and spectral recurrences traditionally rely on static transitions, failing to dynamically revise how stored representations decay or rotate. While recent selective architectures introduce input-dependent transitions, they assign independent controls to every memory mode, coupling control cost to state capacity. We show that high-dimensional spectral memory does not require high-dimensional control, and introduce Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence (SPARC). SPARC employs just two input-dependent scalar signals to coordinate memory retention and phase rotation across heterogeneous complex modes, while preserving mode-specific baseline timescales and frequencies. Its diagonal affine recurrence supports parallel associative scans for sequence-level BPTT as well as exact structured Real-Time Recurrent Learning (RTRL) for online credit assignment. Across partially observable continuous control, POPGym, and sequence classification, SPARC achieves a 9.09% relative return improvement on Walker-P and a 1.36% relative accuracy gain on FordA over second-best methods. On an NVIDIA Blackwell GPU, our implementation reduces recurrent-mixer training latency by 18.2%-34.2% in fixed-token workloads and accelerates scans by 3.1x-4.7x over an optimized RG-LRU baseline. These results show that two shared control signals can efficiently govern adaptive spectral memory across online and full-sequence settings. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39082 — 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 2026-10-07T13:18:10.316Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).