Metraipolis › archive › dc_ba8ef0d0bf4b
Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning — arXiv:2608.23889
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.23889
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:39.134Z
- SHA-256 of the archived text
05273b1abf0025bc201c3ac959f19406d1169ee9c3e4789ec0e121b48d150976- Stable URL of this page
https://metraipolis.com/documento/dc_ba8ef0d0bf4b
How to cite
Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning — arXiv:2608.23889 — arXiv (en), https://arxiv.org/abs/2608.23889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ba8ef0d0bf4b (Metraipolis archive dc_ba8ef0d0bf4b, sha256 05273b1abf0025bc201c3ac959f19406d1169ee9c3e4789ec0e121b48d150976)
BibTeX
@misc{dcba8ef0d0bf4b,
title = {Dimensionless Controls of Plasticity Under Alternating Tasks: From Evolutionary Biology to Continual Learning — arXiv:2608.23889},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.23889},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ba8ef0d0bf4b; sha256 05273b1abf0025bc201c3ac959f19406d1169ee9c3e4789ec0e121b48d150976},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Plasticity under changing environments is central to both evolutionary biology and continual learning. Motivated by recent work on genotype--phenotype maps, we study a minimal deep-learning analogue where a network is trained alternately on two Boolean label sets, and ask which biological controls of plasticity survive the translation to gradient descent. Reinterpreting four proposed biological factors as quantities of training dynamics, we find the system reduces to two dimensionless controls: the task disagreement $r$, the fraction of disagreeing labels, and the reach $\eta T$, the product of learning rate and switching period. We derive two bounds on plasticity: $r$ alone fixes an extremal geometric floor on the utopia distance, while $r$ and $\eta T$ jointly bound forgetting. Across 9,720 trajectories, an ANOVA confirms that $r$, $\eta$, and $T$ dominate, while the effect of neutral-set size (emphasized in the biological setting) is negligible. The optimal reach itself follows an approximate inverse power law $\eta T^{*}\propto r^{-1.18}$, yielding a heuristic that sets the optimal reach $\eta T^*$ from the task disagreement alone. The analogy that survives is therefore dynamical rather than geometric, and our setting enables a view of plasticity through the lens of other driven systems in physics and engineering.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.23889 — 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 2026-10-18T06:28:52.326Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).