Metraipolis › archive › dc_4e66e2171a70
Metaplasticity as adaptive gradient preconditioning for incremental learning — arXiv:2608.14634
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14634
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:39:42.825Z
- SHA-256 of the archived text
2e95ee5e77f7f862a1db8c0434707cf3ecd53f9b95398298b8da9b71640643d9- Stable URL of this page
https://metraipolis.com/documento/dc_4e66e2171a70
How to cite
Metaplasticity as adaptive gradient preconditioning for incremental learning — arXiv:2608.14634 — arXiv (en), https://arxiv.org/abs/2608.14634 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e66e2171a70 (Metraipolis archive dc_4e66e2171a70, sha256 2e95ee5e77f7f862a1db8c0434707cf3ecd53f9b95398298b8da9b71640643d9)
BibTeX
@misc{dc4e66e2171a70,
title = {Metaplasticity as adaptive gradient preconditioning for incremental learning — arXiv:2608.14634},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14634},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e66e2171a70; sha256 2e95ee5e77f7f862a1db8c0434707cf3ecd53f9b95398298b8da9b71640643d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14634. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Biological intelligence naturally prevents catastrophic forgetting through Complementary Learning Systems (CLS) theory, a macroscopic consolidation process driven at the local level by synaptic metaplasticity: the continuous, history-dependent neuromodulation of individual synapses. While artificial neural networks struggle with the stability-plasticity dilemma in non-stationary environments, existing solutions often require task labels or incur massive memory overhead, diverging from biological reality. Re-framing this localized neuromodulation as an optimization-driven process, we introduce $\textbf{SynGAP}$: $\textbf{Syn}$aptic $\textbf{G}$eometric $\textbf{A}$daptive $\textbf{P}$reconditioning. SynGAP is a task-free continual learning framework based on adaptive gradient preconditioning. Rather than relying on explicit episodic triggers, SynGAP simulates real-time metaplasticity by maintaining an exponential moving average of the Fisher Information Matrix over a continuous data stream. During the optimization step, these dynamic metaplastic states are translated into a bounded multiplicative mask that preconditions raw gradients, selectively attenuating updates to critical historical parameters. Empirical evaluations demonstrate SynGAP's superior ability to mitigate catastrophic forgetting compared to established baselines. On the Split CIFAR-100 benchmark, SynGAP delivers a $4\times$ increase in accuracy compared to EWC++ and outperforms Experience Replay (ER) by almost $10\%$, while reducing the forgetting measure by over $10\%$ against both methods. Furthermore, on the CORe50 benchmark, SynGAP achieves about $68\%$, a $10\%$ improvement over optimizer baselines. By mathematically formalizing continuous biological metaplasticity as stable gradient-based regularization, SynGAP offers a highly robust and memory-efficient solution for adaptive intelligence at the edge.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14634 — 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 2026-10-18T19:02:44.020Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).