Geometry of Learning -- L2 Phase Transitions in Deep and Shallow Neural Networks

• URL: http://arxiv.org/abs/2505.06597v1
• Date: Sat, 10 May 2025 11:02:30 GMT
• Title: Geometry of Learning -- L2 Phase Transitions in Deep and Shallow Neural Networks
• Authors: Ibrahim Talha Ersoy, Karoline Wiesner,
• Abstract summary: This paper establishes a unified framework for such transitions by integrating the Ricci curvature of the loss landscape with regularizer-driven deep learning.<n>Our work paves the way for more informed regularization strategies and potentially new methods for probing the intrinsic structure of neural networks beyond the L2 context.
• Score: 0.3683202928838613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When neural networks (NNs) are subject to L2 regularization, increasing the regularization strength beyond a certain threshold pushes the model into an under-parameterization regime. This transition manifests as a first-order phase transition in single-hidden-layer NNs and a second-order phase transition in NNs with two or more hidden layers. This paper establishes a unified framework for such transitions by integrating the Ricci curvature of the loss landscape with regularizer-driven deep learning. First, we show that a curvature change-point separates the model-accuracy regimes in the onset of learning and that it is identical to the critical point of the phase transition driven by regularization. Second, we show that for more complex data sets additional phase transitions exist between model accuracies, and that they are again identical to curvature change points in the error landscape. Third, by studying the MNIST data set using a Variational Autoencoder, we demonstrate that the curvature change points identify phase transitions in model accuracy outside the L2 setting. Our framework also offers practical insights for optimizing model performance across various architectures and datasets. By linking geometric features of the error landscape to observable phase transitions, our work paves the way for more informed regularization strategies and potentially new methods for probing the intrinsic structure of neural networks beyond the L2 context.

Related papers

• Generalized Linear Mode Connectivity for Transformers [87.32299363530996]
  A striking phenomenon is linear mode connectivity (LMC), where independently trained models can be connected by low- or zero-loss paths.<n>Prior work has predominantly focused on neuron re-ordering through permutations, but such approaches are limited in scope.<n>We introduce a unified framework that captures four symmetry classes: permutations, semi-permutations, transformations, and general invertible maps.<n>This generalization enables, for the first time, the discovery of low- and zero-barrier linear paths between independently trained Vision Transformers and GPT-2 models.
  arXiv  Detail & Related papers  (2025-06-28T01:46:36Z)
• New Evidence of the Two-Phase Learning Dynamics of Neural Networks [59.55028392232715]
  We introduce an interval-wise perspective that compares network states across a time window.<n>We show that the response of the network to a perturbation exhibits a transition from chaotic to stable.<n>We also find that after this transition point the model's functional trajectory is confined to a narrow cone-shaped subset.
  arXiv  Detail & Related papers  (2025-05-20T04:03:52Z)
• Phase Transitions in Large Language Models and the $O(N)$ Model [0.0]
  We reformulated the Transformer architecture as an $O(N)$ model to investigate phase transitions in large language models.<n>Our study reveals two distinct phase transitions corresponding to the temperature used in text generation.<n>As an application, the energy of the $O(N)$ model can be used to evaluate whether an LLM's parameters are sufficient to learn the training data.
  arXiv  Detail & Related papers  (2025-01-27T17:36:06Z)
• On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm [47.55215041326702]
  We discover an intriguing linear phenomenon in models that are from a common pretrained checkpoint and finetuned on different tasks, termed as Cross-Task Linearity (CTL) We show that if we linearly interpolate the weights of two finetuned models, the features in the weight-interpolated model are often approximately equal to the linearities of features in two finetuned models at each layer. We conjecture that in the pretraining-finetuning paradigm, neural networks approximately function as linear maps, mapping from the parameter space to the feature space.
  arXiv  Detail & Related papers  (2024-02-06T03:28:36Z)
• Reparameterization through Spatial Gradient Scaling [69.27487006953852]
  Reparameterization aims to improve the generalization of deep neural networks by transforming convolutional layers into equivalent multi-branched structures during training. We present a novel spatial gradient scaling method to redistribute learning focus among weights in convolutional networks.
  arXiv  Detail & Related papers  (2023-03-05T17:57:33Z)
• An Adaptive and Stability-Promoting Layerwise Training Approach for Sparse Deep Neural Network Architecture [0.0]
  This work presents a two-stage adaptive framework for developing deep neural network (DNN) architectures that generalize well for a given training data set. In the first stage, a layerwise training approach is adopted where a new layer is added each time and trained independently by freezing parameters in the previous layers. We introduce a epsilon-delta stability-promoting concept as a desirable property for a learning algorithm and show that employing manifold regularization yields a epsilon-delta stability-promoting algorithm.
  arXiv  Detail & Related papers  (2022-11-13T09:51:16Z)
• Mixed Graph Contrastive Network for Semi-Supervised Node Classification [63.924129159538076]
  We propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN)<n>In our method, we improve the discriminative capability of the latent embeddings by an unperturbed augmentation strategy and a correlation reduction mechanism.<n>By combining the two settings, we extract rich supervision information from both the abundant nodes and the rare yet valuable labeled nodes for discriminative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Exact Phase Transitions in Deep Learning [5.33024001730262]
  We prove that the competition between prediction error and model complexity in the training loss leads to the second-order phase transition for nets with one hidden layer and the first-order phase transition for nets with more than one hidden layer. The proposed theory is directly relevant to the optimization of neural networks and points to an origin of the posterior collapse problem in Bayesian deep learning.
  arXiv  Detail & Related papers  (2022-05-25T06:00:34Z)
• Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks [22.823904789355495]
  We investigate the connection between the mean-fieldhydrodynamic regime and the seminal approach of Saad & Solla. Our work builds on a deterministic description of rates in high-dimensionals from statistical physics.
  arXiv  Detail & Related papers  (2022-02-01T09:45:07Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• Phase diagram for two-layer ReLU neural networks at infinite-width limit [6.380166265263755]
  We draw the phase diagram for the two-layer ReLU neural network at the infinite-width limit. We identify three regimes in the phase diagram, i.e., linear regime, critical regime and condensed regime. In the linear regime, NN training dynamics is approximately linear similar to a random feature model with an exponential loss decay. In the condensed regime, we demonstrate through experiments that active neurons are condensed at several discrete orientations.
  arXiv  Detail & Related papers  (2020-07-15T06:04:35Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.