Orthogonal Polynomial Approximation for Matrix Log Normalization in Global Covariance Pooling

• URL: http://arxiv.org/abs/2608.19021v1
• Date: Wed, 19 Aug 2026 15:17:46 GMT
• Title: Orthogonal Polynomial Approximation for Matrix Log Normalization in Global Covariance Pooling
• Abstract summary: Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recognition.<n>Key ingredient is a mean-eigenvalue pre-normalization that centres the spectrum near 1, away from the singularity of log, with a post-compensation that returns the singular part of log(A) in closed form.
• Score: 11.561251776738324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recognition. Because covariance matrices live on the Symmetric Positive Definite (SPD) manifold, a normalization step is required before the Euclidean classifier. The faithful choice is the matrix logarithm (MLN-COV), which maps the SPD manifold to its tangent space; in practice it was abandoned in favour of the matrix square root because its eigendecomposition-based gradient is numerically unstable. We show that this instability is an artifact of computing the logarithm spectrally, not of the logarithm itself. Approximating the logarithm with finite polynomials in the covariance matrix removes the eigendecomposition from both passes: every operation becomes a General Matrix Multiplication (GEMM), the gradient stays bounded on the spectral support of the pre-normalized covariance, and the unstable 1/(lambda_i-lambda_j) term never appears. The key ingredient is a mean-eigenvalue pre-normalization that centres the spectrum near 1, away from the singularity of log, with a scalar post-compensation that returns the singular part of log(A) in closed form. Our recommended normalizer is a degree-8 Chebyshev expansion evaluated by a three-term matrix recurrence, with a matching reverse recurrence for the backward pass; Legendre, Laguerre, Taylor and Pade expansions are studied as controls that isolate the roles of the basis and of the target function. On three fine-grained benchmarks and ImageNet-1k the decomposition-free logarithm is both faster and more accurate than the spectral logarithm and than the square-root approximations it replaces, and at matched basis and degree the log target beats the square-root target, confirming that the gain comes from the faithful Riemannian map rather than from a better polynomial family.

Related papers

• VORT: Adaptive Power-Law Memory for NLP Transformers [0.913755431537592]
  We introduce a memory architecture in which each ingested token is assigned a learnable fractional order _iin[,1]<n>Because the fractional weighted sum is non-Markovian, we approximate it through a sum-of-exponentials (SOE) decomposition computed by Gauss--Laguerre quadrature.<n>Retrieval is keyed and associative via a linear-attention accumulator with an exact O(KSd_d_v) -per-step recurrence.
  arXiv  Detail & Related papers  (2026-05-09T14:20:17Z)
• Muon Dynamics as a Spectral Wasserstein Flow [21.689846521201588]
  We introduce a family of Wasserstein norms on positive semidefinite matrices.<n>We prove the equivalence between the static and dynamic Benamou-Brenier formulations.<n>We identify exact gradientity associated with flow models.
  arXiv  Detail & Related papers  (2026-04-06T17:41:12Z)
• Robust Automatic Differentiation of Square-Root Kalman Filters via Gramian Differentials [3.542663650865005]
  Square-root Kalman filters propagate state covariances in Cholesky-factor form for numerical stability.<n>Their core operation, triangularization of a matrix $M in mathbbRn times m$, is computed via a QR decomposition in practice.<n>We extend it to rank-deficient inputs via a two-component decomposition: a column-space term based on the Moore--Penrose pseudoinverse, and a null-space correction for perturbations outside the column space of $M$.
  arXiv  Detail & Related papers  (2026-03-13T19:55:08Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Linear combination of unitaries with exponential convergence [0.0]
  We present a general method for decomposing non-unitary operators into a linear combination of unitary operators.<n>When implemented in a quantum circuit, the subnormalisation of the resulting block encoding scales with the double logarithm of the inverse error.
  arXiv  Detail & Related papers  (2026-01-25T22:47:21Z)
• Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry [63.694184882697435]
  Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations.<n>This paper provides a comprehensive and unified understanding of the matrix logarithm and power from a Riemannian geometry perspective.
  arXiv  Detail & Related papers  (2024-07-15T07:11:44Z)
• Stochastic Parallelizable Eigengap Dilation for Large Graph Clustering [12.544602297450533]
  We aim to identify clusters of nodes where most edges fall within clusters and only few edges fall between clusters. A core step of spectral clustering is performing an eigendecomposition of the corresponding graph Laplacian matrix. This paper introduces a parallelizable approach to dilating the spectrum in order to accelerate SVD solvers and in turn, spectral clustering.
  arXiv  Detail & Related papers  (2022-07-29T10:13:07Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration [115.1954841020189]
  We study the inequality and non-asymptotic properties of approximation procedures with Polyak-Ruppert averaging. We prove a central limit theorem (CLT) for the averaged iterates with fixed step size and number of iterations going to infinity.
  arXiv  Detail & Related papers  (2020-04-09T17:54:18Z)
• Multi-Objective Matrix Normalization for Fine-grained Visual Recognition [153.49014114484424]
  Bilinear pooling achieves great success in fine-grained visual recognition (FGVC) Recent methods have shown that the matrix power normalization can stabilize the second-order information in bilinear features. We propose an efficient Multi-Objective Matrix Normalization (MOMN) method that can simultaneously normalize a bilinear representation.
  arXiv  Detail & Related papers  (2020-03-30T08:40:35Z)

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.