Flag Varieties: A Geometric Framework for Deep Network Alignment

• URL: http://arxiv.org/abs/2605.09861v1
• Date: Mon, 11 May 2026 01:46:17 GMT
• Title: Flag Varieties: A Geometric Framework for Deep Network Alignment
• Abstract summary: Alignment, the tendency of adjacent weight matrices in deep networks to develop compatible subspace orientations, underlies gradient flow, Neural Collapse, and representation similarity across architectures.<n>We prove that alignment geometry has a canonical closed, polystable stratum given by a flag variety.<n>We give a geometric explanation of the Level-2/3 hierarchy in Neural Collapse from first principles rather than post-hoc analysis.
• Score: 1.4273866043218153
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Alignment, the tendency of adjacent weight matrices in deep networks to develop compatible subspace orientations, underlies gradient flow, Neural Collapse, and representation similarity across architectures. Despite extensive empirical documentation, these phenomena have resisted unified theoretical treatment: existing explanations are post-hoc, each fitted to a specific observation with whatever mathematics is at hand. We reverse this direction by deriving the mathematical structure that layerwise alignment inherently demands. Using geometric invariant theory, we prove that alignment geometry has a canonical closed, polystable stratum given by a flag variety, and that subspace intersection dimension is its unique reparameterization-invariant observable, establishing that subspace metrics are not empirical conventions but mathematical necessities. This unified framework yields two dynamical consequences: ridge regularization drives subspace alignment at an exponential rate set by weight decay, whereas nonlinear activations induce a commutator obstruction to exact basis alignment, generically present in nonlinear networks and absent in linear ones. Together these give a geometric explanation of the Level-2/3 hierarchy in Neural Collapse from first principles rather than post-hoc analysis. The commutator magnitude and head subspace overlap further serve as weight-space windows into internal alignment structure, requiring no forward passes. Experiments on multilayer perceptrons, residual networks, and pretrained language models support the proposed diagnostics and delineate their scope.

Related papers

• A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning [52.452902154360565]
  We introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning.<n>MCBP explicitly models the intrinsic curvature of the data manifold and computes pointwise mean curvature without requiring principled manifold parametrization.<n>Experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance.
  arXiv  Detail & Related papers  (2026-05-05T20:19:09Z)
• 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)
• An Equivariance Toolbox for Learning Dynamics [13.651450618432094]
  We develop a general equivariance toolbox that yields coupled first- and second-order constraints on learning dynamics.<n>At the first order, our framework unifies conservation laws and implicit-bias relations as special cases of a single identity.<n>At the second order, it provides structural predictions about curvature.
  arXiv  Detail & Related papers  (2025-12-24T23:42:07Z)
• The Neural Differential Manifold: An Architecture with Explicit Geometric Structure [8.201374511929538]
  This paper introduces the Neural Differential Manifold (NDM), a novel neural network architecture that explicitly incorporates geometric structure into its fundamental design.<n>We analyze the theoretical advantages of this approach, including its potential for more efficient optimization, enhanced continual learning, and applications in scientific discovery and controllable generative modeling.
  arXiv  Detail & Related papers  (2025-10-29T02:24:27Z)
• Native Logical and Hierarchical Representations with Subspace Embeddings [25.274936769664098]
  We introduce a novel paradigm: embedding concepts as linear subspaces.<n>It naturally supports set-theoretic operations like intersection (conjunction) and linear sum (disjunction)<n>Our method achieves state-of-the-art results in reconstruction and link prediction on WordNet.
  arXiv  Detail & Related papers  (2025-08-21T18:29:17Z)
• Learning Latent Graph Geometry via Fixed-Point Schrödinger-Type Activation: A Theoretical Study [1.1745324895296467]
  We develop a unified theoretical framework for neural architectures with internal representations evolving as stationary states of dissipative Schr"odinger-type dynamics on learned latent graphs.<n>We prove existence, uniqueness, and smooth dependence of equilibria, and show that the dynamics are equivalent under the Bloch map to norm-preserving Landau--Lifshitz flows.<n>The resulting model class provides a compact, geometrically interpretable, and analytically tractable foundation for learning latent graph geometry via fixed-point Schr"odinger-type activations.
  arXiv  Detail & Related papers  (2025-07-27T00:35:15Z)
• Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation [79.27003481818413]
  We introduce FlatVI, a training framework that regularises the latent manifold of discrete-likelihood variational autoencoders towards Euclidean geometry.<n>By encouraging straight lines in the latent space to approximate geodesics on the decoded single-cell manifold, FlatVI enhances compatibility with downstream approaches.
  arXiv  Detail & Related papers  (2025-07-15T23:08:14Z)
• 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)
• Equivariant non-linear maps for neural networks on homogeneous spaces [8.944149301388551]
  We present a novel framework for non-linear equivariant neural network layers on homogeneous spaces.<n>We derive generalized steerability constraints that any such layer needs to satisfy.<n>We demonstrate how several common equivariant network architectures may be derived from our framework.
  arXiv  Detail & Related papers  (2025-04-29T17:42:56Z)
• Coordinate Independent Convolutional Networks -- Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds [70.32518963244466]
  A major complication in comparison to flat spaces is that it is unclear in which alignment a convolution kernel should be applied on a manifold. We argue that the particular choice of coordinatization should not affect a network's inference -- it should be coordinate independent. A simultaneous demand for coordinate independence and weight sharing is shown to result in a requirement on the network to be equivariant.
  arXiv  Detail & Related papers  (2021-06-10T19:54:19Z)
• Revealing the Structure of Deep Neural Networks via Convex Duality [70.15611146583068]
  We study regularized deep neural networks (DNNs) and introduce a convex analytic framework to characterize the structure of hidden layers. We show that a set of optimal hidden layer weights for a norm regularized training problem can be explicitly found as the extreme points of a convex set. We apply the same characterization to deep ReLU networks with whitened data and prove the same weight alignment holds.
  arXiv  Detail & Related papers  (2020-02-22T21:13:44Z)

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.