Geometric and Spectral Alignment for Deep Neural Network II

• URL: http://arxiv.org/abs/2605.02111v1
• Date: Mon, 04 May 2026 00:17:48 GMT
• Title: Geometric and Spectral Alignment for Deep Neural Network II
• Abstract summary: This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains.<n>Starting from Cartan-coordinate rigidity and fitted effective-rank windows, we study how dominant singular subspaces are transported across adjacent layers.<n>The main results are deterministic, margin-verified results.
• Score: 12.227949990332363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper develops the angular and static-channel component of Geometric and Spectral Alignment for residual Jacobian chains. Starting from Cartan-coordinate rigidity and fitted effective-rank windows, we study how dominant singular subspaces are transported across adjacent layers and how the resulting finite matrices can be displayed in physical channel coordinates. The main results are deterministic, margin-verified results. We bound the error between full interface transport and its dominant-window truncation, add fitted-tail errors so that empirical spectra can be certified against the Gibbs--Cartan tail model, and distinguish source-mode incidence from fully physical input-output channel incidence. Given row groups and active supports, the Physical Alignment Matrix decomposes orthogonally as core plus overlap plus noise. Active-column gaps, pairwise overlap margins, and noise bounds combine into a static certificate radius under which the full transport and the truncated transport induce the same active supports, pairwise incidence graph, SRS sets, hub columns, and core/overlap/noise masks. The finer SC/SA/ST labels of the Invariant Channel Mapping require additional row-energy and profile-correlation margins, stated as explicit perturbation tests. The empirical section reports the matrices and block-energy heatmaps that measure these certificate quantities across CNNs, language models, and vision/diffusion backbones. The figures are interpreted as finite-dimensional measurements; complete membership in the Physical GSA certificate domain requires checking the numerical margin protocol stated in Section 10.

Related papers

• Support Topology and Gradient Mixing in Sinkhorn Layers [0.0]
  We show that each row-column cycle induces a row-stochastic operator on column-potential perturbations modulo constants.<n>We derive the accompanying score and marginal source terms and use Dobrushin contraction and minorization to bound homogeneous and source-driven tail cotangents.
  arXiv  Detail & Related papers  (2026-09-07T20:18:56Z)
• From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers [53.505136935517925]
  Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood.<n>We prove that single-head attention (SHA) is exactly a connection propagation step with constant transport.<n>We find that trained Transformers across scales (from 124M to 8B) and structures (encoder/decoder) exhibit geometric structure consistent with our theory.
  arXiv  Detail & Related papers  (2026-07-12T09:44:54Z)
• CaSPECT: Discovering Causally Homogeneous Subgroups via Directed Spectral Clustering [16.993547305381327]
  CaSPECT defines similarity through the topology of a learned directed acyclic graph (DAG)<n>A novel emphOrientation Validation Score (OVS) combines PC bootstrap evidence with DirectLiNGAM to orient edges robustly.<n>Chung's directed Laplacian provides a spectral embedding in which individuals close together share the same causal propagation pathways.
  arXiv  Detail & Related papers  (2026-07-03T14:20:22Z)
• Self-Certifying Transport MCMC via Dual Spectral-Gap Certificates [3.8549131582427303]
  CerT-MCMC is a framework that equips learned-transport Markov chain Monte Carlo with rigorous convergence certificates.<n>We develop two complementary certificates: The covering certificate bounds the weight-ratio oscillation over the full proposal support via finite-sample covering arguments.<n>The quantile-core certificate restricts attention to a high-probability residual core on which the oscillation is controlled by one-dimensional empirical quantiles.
  arXiv  Detail & Related papers  (2026-05-29T01:31:56Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.68391670109433]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• Geometric and Spectral Alignment for Deep Neural Network I [12.227949990332363]
  We prove deterministic quotient-geometric estimates for singular spectra of Frobenius-normalized layer factors.<n>Full-rank factors are mapped from $mathrmGL(d)$ to the positive cone by $Amapsto Atop A$, then to ordered eigenvalue data.<n>We prove approximate-power-law and metric-chart versions, converse lower bounds, Fisher--KL/Bures action estimates, and near-identity expansions for normalized residual chains.
  arXiv  Detail & Related papers  (2026-05-04T00:07:24Z)
• Sector-dominant graph-local drivers for path-window barrier Hamiltonians on the Boolean hypercube [0.0]
  We study finite-size adiabatic state preparation on Boolean hypercubes.<n>We use graph-local drivers built from sector/path coordinates related to monotone Gray-code representatives.<n>We provide code, finite certificates, CSV files, validation logs, and reproduction scripts to make the finite-size claims traceable.
  arXiv  Detail & Related papers  (2026-04-28T10:54:42Z)
• Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning [52.452902154360565]
  GTSA-PCA is a geometric extension of Principal Component Analysis.<n>It integrates curvature awareness and geodesic consistency within a unified spectral framework.<n>Our results position GTSA-PCA as a principled bridge between statistical and geometric approaches to dimensionality reduction.
  arXiv  Detail & Related papers  (2026-04-20T20:36:36Z)
• Polyhedral Unmixing: Bridging Semantic Segmentation with Hyperspectral Unmixing via Polyhedral-Cone Partitioning [2.4851820343103035]
  We propose a direct segmentation-to-unmixing pipeline that performs blind hyperspectral unmixing from semantic segmentation.<n>Because the segmentation method can be freely chosen, the user gains explicit control over the unmixing process.<n> experiments on three real datasets demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2026-03-31T08:46:09Z)
• Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition [51.56484100374058]
  This paper formulates pilot-limited channel estimation as low-rank tensor completion from sparse observations.<n>Experiments on synthetic channels demonstrate 10-20,dB normalized mean-square error (NMSE) improvement over least-squares (LS)<n> evaluations on DeepMIMO ray-tracing channels show 24-44% additional NMSE reduction over pure tensor-based methods.
  arXiv  Detail & Related papers  (2026-02-03T23:38:05Z)
• Data-Driven Graph Filters via Adaptive Spectral Shaping [10.449640808601199]
  We introduce Adaptive Spectral Shaping, a data-driven framework for graph filtering.<n>The framework provides compact spectral modules that plug into graph signal processing pipelines and graph neural networks.
  arXiv  Detail & Related papers  (2026-02-03T16:20:49Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors [71.44213719783703]
  Intra-group Consistency Augmentation Framework (ICAF) developed to label Cadmium Zinc Telluride (CdZnTe) semiconductor images.<n>ICAF consists of two key modules, the View Augmentation Module (VAM) and the View Correction Module (VCM)<n>ICAF achieves a 70.6% mIoU on the CdZnTe dataset using only 2 group-annotated data.
  arXiv  Detail & Related papers  (2025-08-18T09:40:36Z)
• Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization [13.021238902084647]
  Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features.<n>We introduce SGPC (Sheaf GNNs with PAC-Bayes), a unified architecture that combines cellular-sheaf message passing with several mechanisms.<n> Experiments on nine homophilic and heterophilic benchmarks show that SGPC outperforms state-of-the-art spectral and sheaf-based GNNs.
  arXiv  Detail & Related papers  (2025-08-01T06:39:28Z)
• SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation [58.61946589036262]
  This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. We propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT.
  arXiv  Detail & Related papers  (2022-03-29T02:48:08Z)
• Spectral embedding and the latent geometry of multipartite networks [47.18054692085814]
  Many networks are multipartite, meaning that they contain nodes of fundamentally different types.<n>This paper demonstrates that the node representations obtained via spectral embedding lie near type-specific low-dimensional subspaces of a higher-dimensional ambient space.<n>We propose a follow-on step after spectral embedding, to recover node representations in their intrinsic rather than ambient dimension.
  arXiv  Detail & Related papers  (2022-02-08T15:52:03Z)

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.