The Geometric Structure of Models Learning Sparse Data

• URL: http://arxiv.org/abs/2605.08464v2
• Date: Fri, 15 May 2026 13:15:46 GMT
• Title: The Geometric Structure of Models Learning Sparse Data
• Abstract summary: We describe the regimes where the manifold hypothesis is not applicable as sparse.<n>We demonstrate that models succeed in the sparse regime by exploiting a highly structured local geometry.<n>We introduce GrokAlign, a regularization strategy that actively induces normal alignment.
• Score: 25.675653468258805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The manifold hypothesis (MH) is often used to explain how machine learning can overcome the curse of dimensionality. However, the MH is only applicable in regimes where the training data provides a sufficiently dense sample of the underlying low-dimensional data manifold, or where such a low-dimensional manifold is conceivably present. We describe the regimes where the MH is not applicable as sparse. In this paper, we demonstrate that models succeed in the sparse regime by exploiting a highly structured local geometry, a property we formalize as normal alignment. We prove that normal-aligned classifiers -- whose input-output Jacobians are rank-one and align perfectly with the training data -- minimize the training objective under norm constraints and achieve maximal local robustness under a non-zero Jacobian constraint. For continuous piecewise-affine deep networks, normal alignment manifests geometrically as centroid alignment within the network's induced power diagram partition and results from the feature-learning regime. Motivated by these theoretical insights, we introduce GrokAlign, a regularization strategy that actively induces normal alignment. We demonstrate that GrokAlign significantly accelerates the training dynamics of deep networks relevant to the grokking phenomenon. Furthermore, we apply the principle of normal alignment to Recursive Feature Machines (RFMs) to introduce Recursive Feature Alignment Machines (RFAMs). We show that RFAMs exhibit greater adversarial robustness compared to RFMs when trained on tabular data.

Related papers

• Why Self-Supervised Encoders Want to Be Normal [0.0]
  We show that the preference for normal distributions in self-supervised encoders is a direct consequence of the Information Bottleneck (IB) principle.<n>Under this framework, we show that latent representations correspond to soft clustering of inputs sharing similar predictive distributions.<n>This perspective unifies a wide range of existing supervised and less-supervised objectives and provides a principled explanation for commonly used regularization schemes.
  arXiv  Detail & Related papers  (2026-04-30T11:33:05Z)
• The Inductive Bias of Convolutional Neural Networks: Locality and Weight Sharing Reshape Implicit Regularization [57.37943479039033]
  We study how architectural inductive bias reshapes the implicit regularization induced by the edge-of-stability phenomenon in gradient descent.<n>We show that locality and weight sharing fundamentally change this picture.
  arXiv  Detail & Related papers  (2026-03-05T04:50:51Z)
• SIGMA: Scalable Spectral Insights for LLM Collapse [51.863164847253366]
  We introduce SIGMA (Spectral Inequalities for Gram Matrix Analysis), a unified framework for model collapse.<n>By utilizing benchmarks that deriving and deterministic bounds on the matrix's spectrum, SIGMA provides a mathematically grounded metric to track the contraction of the representation space.<n>We demonstrate that SIGMA effectively captures the transition towards states, offering both theoretical insights into the mechanics of collapse.
  arXiv  Detail & Related papers  (2026-01-06T19:47:11Z)
• Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning [52.26396748560348]
  We provide an overview of high dimensional dynamical systems driven by random matrices.<n>We focus on applications to simple models of learning and generalization in machine learning theory.
  arXiv  Detail & Related papers  (2026-01-03T00:12:32Z)
• ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models [0.0]
  We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA)<n>It improves reasoning, alignment and robustness by treating an organisation's policies/principles as directions to move on a model's information manifold.
  arXiv  Detail & Related papers  (2025-10-13T11:13:09Z)
• Reconstruction of SINR Maps from Sparse Measurements using Group Equivariant Non-Expansive Operators [1.9692747349111241]
  We introduce a novel reconstruction framework based on Group Equivariant Non-Expansive Operators (GENEOs)<n>Our key insight is that for network management, preserving the topological structure of the SINR map, is often more critical than minimizing pixel-wise error.<n>Results show that while maintaining competitive MSE, our method dramatically outperforms established ML baselines in topological fidelity.
  arXiv  Detail & Related papers  (2025-07-25T14:59:44Z)
• Matrix Completion-Informed Deep Unfolded Equilibrium Models for Self-Supervised k-Space Interpolation in MRI [8.33626757808923]
  Regularization model-driven deep learning (DL) has gained significant attention due to its ability to leverage the potent representational capabilities of DL. We propose a self-supervised DL approach for accelerated MRI that is theoretically guaranteed and does not rely on fully sampled labels.
  arXiv  Detail & Related papers  (2023-09-24T07:25:06Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Atlas Based Representation and Metric Learning on Manifolds [0.0]
  We explore the use of a topological manifold, represented as a collection of charts, as the target space of neural network based representation learning tasks. This is achieved by a simple adjustment to the output of an encoder's network architecture plus the addition of a maximal mean discrepancy (MMD) based loss function for regularization.
  arXiv  Detail & Related papers  (2021-06-13T18:05:46Z)
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior [78.58159882218378]
  We propose to employ explicit manifold learning as prior to alleviate mode collapse and stabilize training of GAN. Our experiments on both the toy data and real datasets show the effectiveness of MMCGAN in alleviating mode collapse, stabilizing training, and improving the quality of generated samples.
  arXiv  Detail & Related papers  (2020-06-18T07:38:54Z)
• 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.