Metaplasticity as adaptive gradient preconditioning for incremental learning

[2608.14634] Metaplasticity as adaptive gradient preconditioning for incremental learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2608.14634 (cs) [Submitted on 27 Jul 2026] Title: Metaplasticity as adaptive gradient preconditioning for incremental learning Authors: Isabelle Aguilar , Zayn Andre Zainal , Omid Kavehei View a PDF of the paper titled Metaplasticity as adaptive gradient preconditioning for incremental learning, by Isabelle Aguilar and 2 other authors View PDF HTML (experimental) Abstract: 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. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2608.14634 [cs.LG] (or arXiv:2608.14634v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2608.14634 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Isabelle Aguilar [ view email ] [v1] Mon, 27 Jul 2026 21:45:37 UTC (6,325 KB) Full-text links: Access Paper: View a PDF of the paper titled Metaplasticity as adaptive gradient preconditioning for incremental learning, by Isabelle Aguilar and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Random Reshuffling Dominates Stochastic Gradient Descent#324881
• BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning#13103
• Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives#1143267
• Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning#1144357
• Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise#1012349