Abstract:Gradient-based algorithms are a cornerstone of artificial neural network training, yet it remains unclear whether biological neural networks use similar gradient-based strategies during learning. Experiments often discover a diversity of synaptic plasticity rules, but whether these amount to an approximation to gradient descent is unclear. Here we investigate a previously overlooked possibility: that learning dynamics may include fundamentally non-gradient "curl"-like components while still being able to effectively optimize a loss function. Curl terms naturally emerge in networks with inhibitory-excitatory connectivity or Hebbian/anti-Hebbian plasticity, resulting in learning dynamics that cannot be framed as gradient descent on any objective. To investigate the impact of these curl terms, we analyze feedforward networks within an analytically tractable student-teacher framework, systematically introducing non-gradient dynamics through neurons exhibiting rule-flipped plasticity. Small curl terms preserve the stability of the original solution manifold, resulting in learning dynamics similar to gradient descent. Beyond a critical value, strong curl terms destabilize the solution manifold. Depending on the network architecture, this loss of stability can lead to chaotic learning dynamics that destroy performance. In other cases, the curl terms can counterintuitively speed learning compared to gradient descent by allowing the weight dynamics to escape saddles by temporarily ascending the loss. Our results identify specific architectures capable of supporting robust learning via diverse learning rules, providing an important counterpoint to normative theories of gradient-based learning in neural networks.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.02765 [cs.LG] |
| (or arXiv:2510.02765v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.02765 arXiv-issued DOI via DataCite |
From: Hugo Ninou [view email]
[v1]
Fri, 3 Oct 2025 06:54:40 UTC (1,943 KB)
[v2]
Thu, 9 Oct 2025 15:58:43 UTC (2,179 KB)
[v3]
Mon, 13 Oct 2025 09:45:32 UTC (2,225 KB)
[v4]
Tue, 28 Apr 2026 13:10:33 UTC (2,222 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。