mlsanityData to 14 Oct 2026

Kernel Logistic Regression Learning for High-Capacity Hopfield Networks

arXiv 2504.07633 ↗First posted 10 Apr 2025cs.LG cs.NEcited by 7

Not on the map. Why?

Abstract (arXiv)

Hebbian learning limits Hopfield network storage capacity (pattern-to-neuron ratio around 0.14). We propose Kernel Logistic Regression (KLR) learning. Unlike linear methods, KLR uses kernels to implicitly map patterns to high-dimensional feature space, enhancing separability. By learning dual variables, KLR dramatically improves storage capacity, achieving perfect recall even when pattern numbers exceed neuron numbers (up to ratio 1.5 shown), and enhances noise robustness. KLR demonstrably outperforms Hebbian and linear logistic regression approaches.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 1 of its 8 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

1 of 8 references.

References · 1

  1. 2022Kernel Memory Networks: A Unifying Framework for Memory Modelingcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Self-Organization and Spectral Mechanism of Attractor Landscapes in High-Capacity Kernel Hopfield Networkscited by 5
  2. 2025Quantitative Attractor Analysis of High-Capacity Kernel Hopfield Networkscited by 4
  3. 2025Kernel Ridge Regression for Efficient Learning of High-Capacity Hopfield Networkscited by 1
  4. 2026Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memorycited by 1
  5. 2026Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networkscited by 0
  6. 2026Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimizationcited by 0
  7. 2026Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memoriescited by 0