Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks

[2505.01218] Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2505.01218 (cs) [Submitted on 2 May 2025 ( v1 ), last revised 10 Apr 2026 (this version, v8)] Title: Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks Authors: Akira Tamamori View a PDF of the paper titled Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks, by Akira Tamamori View PDF HTML (experimental) Abstract: Kernel-based learning methods such as Kernel Logistic Regression (KLR) can substantially increase the storage capacity of Hopfield networks, but the principles governing their performance and stability remain largely uncharacterized. This paper presents a comprehensive quantitative analysis of the attractor landscape in KLR-trained networks to establish a solid foundation for their design and application. Through extensive, statistically validated simulations, we address critical questions of generality, scalability, and robustness. Our comparative analysis shows that KLR and Kernel Ridge Regression (KRR) exhibit similarly high storage capacities and clean attractor landscapes under typical operating conditions, suggesting that this behavior is a general property of kernel regression methods, although KRR is computationally much faster. We identify a non-trivial, scale-dependent law for the kernel width $\gamma$, demonstrating that optimal capacity requires $\gamma$ to be scaled such that $\gamma N$ increases with network size $N$. This finding implies that larger networks require more localized kernels, in which each pattern's influence is more spatially confined, to mitigate inter-pattern interference. Under this optimized scaling, we provide clear evidence that storage capacity scales linearly with network size~($P \propto N$). Furthermore, our sensitivity analysis shows that performance is remarkably robust with respect to the choice of the regularization parameter $\lambda$. Collectively, these findings provide a concise set of empirical principles for designing high-capacity and robust associative memories and clarify the mechanisms that enable kernel methods to overcome the classical limitations of Hopfield-type models. Comments: 17 pages, 7 figures; accepted to NOLTA, IEICE Subjects: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE) Cite as: arXiv:2505.01218 [cs.LG] (or arXiv:2505.01218v8 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2505.01218 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Akira Tamamori [ view email ] [v1] Fri, 2 May 2025 12:13:23 UTC (574 KB) [v2] Wed, 19 Nov 2025 04:51:47 UTC (2,888 KB) [v3] Fri, 21 Nov 2025 07:10:33 UTC (3,066 KB) [v4] Mon, 24 Nov 2025 04:42:20 UTC (3,066 KB) [v5] Fri, 28 Nov 2025 03:07:37 UTC (3,066 KB) [v6] Sat, 6 Dec 2025 15:18:51 UTC (3,067 KB) [v7] Fri, 9 Jan 2026 06:47:39 UTC (3,067 KB) [v8] Fri, 10 Apr 2026 05:43:53 UTC (3,067 KB) Full-text links: Access Paper: View a PDF of the paper titled Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networks, by Akira Tamamori View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2025-05 Change to browse by: cs cs.NE 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

• Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory#1123836
• Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory#919378
• Risk-Sensitive Learning in Population Games under Extreme Events: Bifurcations and Chaotic Dynamics#1052218
• Stochastic Gradient Tracking over Time-Varying Networks: One-Step Lyapunov Analysis#620676
• Stochastic Gradient Tracking over Time-Varying Networks: One-Step Lyapunov Analysis#618997