The paper tackles two key gaps in streaming PCA using Oja's algorithm: it establishes sharp operator‑norm convergence for general‑rank subspaces under sub‑Gaussian data, and it provides distributional inference for the resulting subspace estimator. The authors remove non‑vanishing remainder terms from existing analyses, achieving rates that match minimax bounds in both dense‑tail and sparse‑tail regimes. They further develop a linearization of Oja’s iterates, enabling high‑dimensional Gaussian approximations and an online multiplier bootstrap for practical inference.
By Haoshu Xu, Hongzhe Li
arXiv:2603. 19703v2 Announce Type: replace-cross Abstract: Estimating covariance matrices is fundamental to a wide range of statistical applications.
By T. Tony Cai, Yicheng Li
arXiv:2605. 11607v2 Announce Type: replace-cross Abstract: Probabilistic partial least squares (PPLS) is a central likelihood-based model for two-view learning when one needs both interpretable latent factors and calibrated uncertainty.
By Haoran Hu, Xingce Wang
arXiv:2609. 02155v1 Announce Type: new Abstract: The Johnson-Lindenstrauss (JL) lemma guarantees that a random projection of $n$ points to $m=O(\varepsilon^{-2}\log n)$ dimensions preserves pairwise squared distances within relative error $\varepsilon$ with high probability, and this dimension order is asymptotically optimal.
By Piyush Sao
arXiv:2505. 10882v2 Announce Type: replace Abstract: Principal component analysis classically requires full $d$-dimensional samples, yet in various applications hardware limits acquisition to a few scalar measurements per sample.
By Alex Saad-Falcon, Brighton Ancelin, Justin Romberg
arXiv:2603. 11308v3 Announce Type: replace Abstract: Principal Component Analysis (PCA) is a cornerstone of dimensionality reduction, yet its classical formulation relies critically on second-order moments and is therefore fragile in the presence of heavy-tailed data and impulsive noise.
By Mario Sayde, Christopher Khater, Jihad Fahs, Ibrahim Abou-Faycal
The paper introduces a new representation‑adaptive kernel class that, on a fixed sample, yields a union of reproducing‑kernel Hilbert‑space ellipsoids instead of a single ellipsoid. It defines a minimum‑trace common covariance dominating the empirical union generated by Brownian kernel ladders, and derives exact formulations, statistical and computational consequences, and a universal Gaussian‑complexity bound. The work further develops geometric reductions, deterministic depth laws, and exact empirical Kolmogorov‑width formulas, providing both lower and upper certificates for covariance certification and illustrating the distinction between successful covariance certification and predictive selection.
By Mahdi Mohammadigohari
arXiv:2608.30374v1 Announce Type: cross
Abstract: We study null-space estimation from a noisy matrix. For a simple left null space, we first derive an exact compact expression for the error of the sm...
By Xin Li, Jonathan Cohen, Rami Puzis
arXiv:2606. 03559v1 Announce Type: new Abstract: For nonconvex optimization problems whose objective is the prediction function of a trained Support Vector Regression (SVR) model with the Gaussian radial basis function (RBF) kernel (RBF-SVR), we present a framework that applies the difference of convex functions (DC) algorithm (DCA) by exploiting the analytical structure of the RBF kernel to construct an explicit DC decomposition.
By Yohei Kakimoto, Yuto Omae, Hirotaka Takahashi
The paper introduces a copula-based framework to relate Data‑Consistent Inversion (DCI) and its iterative variant (iDCI). By applying Sklar’s theorem, the authors factor the DCI update into marginal and dependence components, showing that any remaining discrepancy after iDCI convergence is fully captured by the copulas of the observed and predicted joint distributions. They prove that an exact copula transformation recovers the original DCI solution and provide convergence results for approximate transformations, supported by numerical examples illustrating adaptive refinement and progressive problem refinement.
By Troy Butler, Tianyi Jiang, Jo\~ao Silva, Harri Hakula, Timothy Wildey
The paper introduces the spherical Cauchy distribution as a new hyperspherical posterior for variational autoencoders, avoiding the complications of the von Mises–Fisher and Power Spherical alternatives. By using stereographic projection and a Möbius transformation, the authors obtain exact posterior samples and a closed‑form KL divergence that terminates in a finite polynomial for even dimensions and admits certified truncation for odd dimensions. Empirical results show that the spherical Cauchy yields faster inference and lower reconstruction loss on MNIST and improved negative log‑likelihood on smallNORB compared to existing methods.
By Lukas Sablica, Kurt Hornik
arXiv:2606. 25169v1 Announce Type: cross Abstract: Sampling from an unnormalized target by reversing an Ornstein--Uhlenbeck diffusion requires the score of each noise-perturbed marginal.
By Alois Duston, Tan Bui Tanh