CCAR: Intrinsic Robustness as an Emergent Geometric Property

• URL: http://arxiv.org/abs/2604.16861v1
• Date: Sat, 18 Apr 2026 06:23:24 GMT
• Title: CCAR: Intrinsic Robustness as an Emergent Geometric Property
• Abstract summary: We propose a class-Conditional Activation Regularization (CCAR) to explicitly engineer the feature space.<n>By shaping the latent representation to class energy to subspaces, we create a geometric scaffold that naturally filters noise and adversarial perturbations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Standard supervised learning optimizes for predictive accuracy but remains agnostic to the internal geometry of learned features, often yielding representations that are entangled and brittle. We propose Class-Conditional Activation Regularization (CCAR) to explicitly engineer the feature space, imposing a block-diagonal structure via a soft inductive bias. By shaping the latent representation to confine class energy to orthogonal subspaces, we create an intrinsic geometric scaffold that naturally filters noise and adversarial perturbations. We provide theoretical analysis linking this structural constraint to the maximization of the Fisher Discriminant Ratio, establishing a formal connection between geometric disentanglement and algorithmic stability. Empirically, this approach demonstrates that robustness is an emergent property of a well-engineered feature space, significantly outperforming baselines on label noise and input corruption benchmarks.

Related papers

• Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy [1.1907026010541673]
  This paper introduces a structural taxonomy for constrained non-constrained optimization based on the signature Lagrange multipliers at KKT stationary points.<n>Four vector-free shape features this partition dual space into five operational regimes: Unconstrained, ResourceLimited, Saturation, Strongly--Coupled, and Hybrid.
  arXiv  Detail & Related papers  (2026-08-31T23:22:05Z)
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers [93.3976834364707]
  We propose sREPA, a structural REPresentation Alignment framework to enforce consistency in the relational geometry of feature maps.<n>By encouraging the model to internalize holistic spatial layouts and structural correlations from pre-trained features, sREPA achieves faster and more stable convergence.
  arXiv  Detail & Related papers  (2026-05-16T12:01:04Z)
• 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)
• Intrinsic Pointer Basis and Irreversible Classicality from Coherence Contraction [0.0]
  We analyze the irreversible emergence of classical behavior from a reduced quantum description via a canonical intrinsic decomposition of the density operator.<n>We prove that the quadratic coherence functional is a Lyapunov functional under pure-dephasing or interaction-picture evolution.<n>This yields a canonical state-dependent operational classicality criterion via the normalized cohesion index.
  arXiv  Detail & Related papers  (2026-04-25T13:41:22Z)
• 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)
• Structural Instability of Feature Composition [2.5754366051855837]
  We study the compositional-collapse threshold under a spherical dictionary model.<n>We show that, in the high-bias regime, ReLU converts microscopic correlation-induced variance fluctuations into a systematic drift.<n>We validate the predicted scaling trends on structured semantic features extracted from CLEVR.
  arXiv  Detail & Related papers  (2026-04-18T05:53:31Z)
• Spectral-Transport Stability and Benign Overfitting in Interpolating Learning [0.0]
  We develop a theoretical framework for generalization in the interpolating regime of statistical learning.<n>We prove finite-sample risk bounds, establish a sharp benign-overfitting index, and derive explicit phase-transition rates under spectral decay.<n>The framework also clarifies implicit regularization by showing how dynamics can select interpolating solutions of minimal spectral-transport energy.
  arXiv  Detail & Related papers  (2026-04-09T15:19:00Z)
• The Quadratic Geometry of Flow Matching: Semantic Granularity Alignment for Text-to-Image Synthesis [0.0]
  We analyze the optimization dynamics of generative fine-tuning.<n>Motivated by this insight, we propose Semantic Granularity Alignment (SGA), using Text-to-Image synthesis as a testbed.
  arXiv  Detail & Related papers  (2026-03-11T13:56:53Z)
• First-Order Geometry, Spectral Compression, and Structural Compatibility under Bounded Computation [0.0]
  We propose an operator-theoretic formulation in which limitations are encoded by self-adjoint operators.<n>In this setting, the optimal first-order improvement direction emerges as a pseudoinverse-weighted gradient.<n>We show that effective dynamics concentrate along dominant spectral modes, yielding a principled notion of spectral compression.
  arXiv  Detail & Related papers  (2026-03-09T15:29:41Z)
• Invariance on Manifolds: Understanding Robust Visual Representations for Place Recognition [19.200074425090595]
  We propose a Second-Order Geometric Statistics framework that inherently captures geometric stability without training.<n>Our approach introduces a training-free framework built upon fixed, pre-trained backbones, achieving strong zero-shot generalization without parameter updates.
  arXiv  Detail & Related papers  (2026-01-31T18:12:29Z)
• Riemannian Flow Matching for Disentangled Graph Domain Adaptation [51.98961391065951]
  Graph Domain Adaptation (GDA) typically uses adversarial learning to align graph embeddings in Euclidean space.<n>DisRFM is a geometry-aware GDA framework that unifies embedding and flow-based transport.
  arXiv  Detail & Related papers  (2026-01-31T11:05:35Z)
• Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds [63.47271262149291]
  We propose a unified framework for PAC-Bayesian norm-based generalization.<n>The key to our approach is a sensitivity matrix that quantifies the network outputs with respect to structured weight perturbations.<n>We derive a family of generalization bounds that recover several existing PAC-Bayesian results as special cases.
  arXiv  Detail & Related papers  (2026-01-13T00:42:22Z)
• Limitation of Stoquastic Quantum Annealing: A Structural Perspective [0.0]
  We provide a structural explanation for the anti-crossing arising from the competition between the energies associated with a set of degenerate local minima.<n>This paper serves as a supplementary companion to our main work on the DIC-DAC-DOA algorithm.
  arXiv  Detail & Related papers  (2025-09-18T04:39:48Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings [113.15416137912399]
  We propose and analyze a novel theoretical and algorithmic framework for structured prediction. We study a large class of loss functions that implicitly defines a suitable geometry on the problem. When dealing with output spaces with infinite cardinality, a suitable implicit formulation of the estimator is shown to be crucial.
  arXiv  Detail & Related papers  (2020-02-13T10:30:04Z)

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.