Curl Descent: Non-Gradient Learning Dynamics with Sign-Diverse Plasticity

• URL: http://arxiv.org/abs/2510.02765v3
• Date: Mon, 13 Oct 2025 09:45:32 GMT
• Title: Curl Descent: Non-Gradient Learning Dynamics with Sign-Diverse Plasticity
• Abstract summary: We show that learning dynamics may include fundamentally non-gradient "curl"-like components.<n>Small curl terms preserve the stability of the original solution manifold, resulting in learning dynamics similar to gradient descent.<n>Our results identify specific architectures capable of supporting robust learning via diverse learning rules.
• Score: 1.2744523252873352
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry [52.75288960194919]
  Recent work has identified incremental learning in shallow networks trained on single-index and multi-index models.<n>We introduce a symmetry-based finite-width approximation via symmetrized networks, rather than comparing directly with an infinite-width limit.
  arXiv  Detail & Related papers  (2026-09-09T22:35:31Z)
• The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions [51.68215326304272]
  We show that even small perturbations reliably cause otherwise identical training trajectories to diverge-an effect that diminishes rapidly over training time.<n>Our findings provide insights into neural network training stability, with practical implications for fine-tuning, model merging, and diversity of model ensembles.
  arXiv  Detail & Related papers  (2025-06-16T08:35:16Z)
• Dynamical stability and chaos in artificial neural network trajectories along training [3.379574469735166]
  We study the dynamical properties of this process by analyzing through this lens the network trajectories of a shallow neural network. We find hints of regular and chaotic behavior depending on the learning rate regime. This work also contributes to the cross-fertilization of ideas between dynamical systems theory, network theory and machine learning.
  arXiv  Detail & Related papers  (2024-04-08T17:33:11Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Smooth Exact Gradient Descent Learning in Spiking Neural Networks [0.0]
  We demonstrate exact gradient descent based on continuously changing spiking dynamics.<n>These are generated by neuron models whose spikes vanish and appear at the end of a trial, where it cannot influence subsequent dynamics.
  arXiv  Detail & Related papers  (2023-09-25T20:51:00Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Learning fixed points of recurrent neural networks by reparameterizing the network model [0.0]
  In computational neuroscience, fixed points of recurrent neural networks are commonly used to model neural responses to static or slowly changing stimuli. A natural approach is to use gradient descent on the Euclidean space of synaptic weights. We show that this approach can lead to poor learning performance due to singularities that arise in the loss surface.
  arXiv  Detail & Related papers  (2023-07-13T13:09:11Z)
• Dynamics-aware Adversarial Attack of Adaptive Neural Networks [75.50214601278455]
  We investigate the dynamics-aware adversarial attack problem of adaptive neural networks. We propose a Leaded Gradient Method (LGM) and show the significant effects of the lagged gradient. Our LGM achieves impressive adversarial attack performance compared with the dynamic-unaware attack methods.
  arXiv  Detail & Related papers  (2022-10-15T01:32:08Z)
• Gradient descent in materia through homodyne gradient extraction [2.012950941269354]
  We demonstrate a simple yet efficient gradient extraction method, based on the principle of homodyne detection.<n>By perturbing the parameters that need to be optimized we effectively obtain the gradient information in a highly robust and scalable manner.<n>Homodyne gradient extraction can in principle be fully implemented in materia, facilitating the development of autonomously learning material systems.
  arXiv  Detail & Related papers  (2021-05-15T12:18:31Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)
• Learning to Learn with Feedback and Local Plasticity [9.51828574518325]
  We employ meta-learning to discover networks that learn using feedback connections and local, biologically inspired learning rules. Our experiments show that meta-trained networks effectively use feedback connections to perform online credit assignment in multi-layer architectures.
  arXiv  Detail & Related papers  (2020-06-16T22:49:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.