Scalar Representations of Neural Network Training Dynamics

• URL: http://arxiv.org/abs/2606.30384v1
• Date: Mon, 29 Jun 2026 14:40:03 GMT
• Title: Scalar Representations of Neural Network Training Dynamics
• Abstract summary: Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape.<n>We investigate whether such a scalar embedding provides a meaningful low-dimensional representation of neural network training dynamics.
• Score: 1.9583341377413463
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of trainable parameters makes the direct analysis of these dynamics challenging. In this work, we treat such training trajectories as temporal networks and apply recently proposed strategies for the scalar embedding of temporal networks. We investigate whether such a scalar embedding provides a meaningful low-dimensional representation of neural network training dynamics. Using a multilayer perceptron trained on the MNIST classification task, we show that the embedding preserves the main dynamical features observed in the original parameter space, including the emergence of sensitivity to initial conditions for specific learning rate regimes and an accurate reconstruction of the network's maximum Lyapunov exponent. We then use the embedded scalar trajectory to define a characteristic time, analogous to a Lyapunov time, after which the exponential separation between initially close embedded trajectories saturates. This characteristic time captures the typical decorrelation time between initially close network trajectories in the original high-dimensional system. Finally, we investigate the statistical organization of asymptotic training states through a spacing observable defined in the embedded space. We find that the distributions of rescaled asymptotic spacings collapse onto a common form across initial conditions and are compatible with a skew lognormal distribution. Altogether, our results suggest that scalar low-dimensional embeddings provide a useful framework for studying and visualizing the dynamical properties of neural network optimization trajectories.

Related papers

• rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data [44.17657834678967]
  We propose a novel semi-supervised pre-training strategy to enforce latent representations that satisfy the Neural Collapse phenomenon.<n>We show that our method significantly outperforms previous pretext tasks when applied to LSTMs, transformers, and state-space models.
  arXiv  Detail & Related papers  (2025-08-13T19:16:47Z)
• Leveraging chaos in the training of artificial neural networks [3.379574469735166]
  We explore the dynamics of the neural network trajectory along training for unconventionally large learning rates.<n>We show that for a region of values of the learning rate, the GD optimization shifts away from purely exploitation-like algorithm into a regime of exploration-exploitation balance.
  arXiv  Detail & Related papers  (2025-06-10T07:41:58Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy [75.15685966213832]
  We analyze the rich directional structure of optimization trajectories represented by their pointwise parameters. We show that training only scalar batchnorm parameters some while into training matches the performance of training the entire network.
  arXiv  Detail & Related papers  (2024-03-12T07:32:47Z)
• Implicit regularization of deep residual networks towards neural ODEs [8.075122862553359]
  We establish an implicit regularization of deep residual networks towards neural ODEs. We prove that if the network is as a discretization of a neural ODE, then such a discretization holds throughout training.
  arXiv  Detail & Related papers  (2023-09-03T16:35:59Z)
• Stabilizing RNN Gradients through Pre-training [3.335932527835653]
  Theory of learning proposes to prevent the gradient from exponential growth with depth or time, to stabilize and improve training. We extend known stability theories to encompass a broader family of deep recurrent networks, requiring minimal assumptions on data and parameter distribution. We propose a new approach to mitigate this issue, that consists on giving a weight of a half to the time and depth contributions to the gradient.
  arXiv  Detail & Related papers  (2023-08-23T11:48:35Z)
• How neural networks learn to classify chaotic time series [77.34726150561087]
  We study the inner workings of neural networks trained to classify regular-versus-chaotic time series. We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
  arXiv  Detail & Related papers  (2023-06-04T08:53:27Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)
• Input-to-State Representation in linear reservoirs dynamics [15.491286626948881]
  Reservoir computing is a popular approach to design recurrent neural networks. The working principle of these networks is not fully understood. A novel analysis of the dynamics of such networks is proposed.
  arXiv  Detail & Related papers  (2020-03-24T00:14:25Z)

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.