← Back to all news
arXiv Statistics ML By Ohad Sheelo, Tal Golan, Ari Pakman

Gaussian BROJA Partial Information Decomposition in Closed Form

Read the original on arXiv Statistics ML →

The paper presents a closed‑form solution for the BROJA partial information decomposition (PID) when all variables are jointly Gaussian. This analytic expression eliminates the need for numerical optimization, allowing direct computation of unique, redundant, and synergistic information components in multivariate Gaussian settings. The resulting formula yields speedups of more than two orders of magnitude for high‑dimensional Gaussian PID calculations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv Statistics ML
Oct 7

Redundancy and synergy in multivariate Gaussians via the Blackwell order

The article introduces a partial information decomposition (PID) for multivariate Gaussian systems using the Blackwell order, which determines when one channel is more informative than another. It shows that Gaussian channels optimally extract redundant and union information, providing a geometric interpretation and an efficient numerical algorithm. The authors derive closed‑form expressions for two‑source cases, compare their Blackwell redundancy to the BROJA measures, and demonstrate scalability to systems with up to a thousand dimensions or sources, including an application to an optimal control problem.

By Artemy Kolchinsky
More like this →
arXiv Machine Learning
Oct 9

Don't Get Your Kroneckers in a Twist: Gaussian Processes on High-Dimensional Incomplete Grids

The paper introduces CUTS-GPR, a method for exact Gaussian Process Regression (GPR) in high-dimensional settings. It achieves near-linear scaling in the number of training points and low-order polynomial scaling in dimensionality by using an additive kernel on an incomplete grid, enabling efficient kernel matrix-vector products. Benchmarks demonstrate scalability to billions of data points and thousands of dimensions, with full GPR runs on up to 4.5 million points in 500 dimensions and practical application to ten high-dimensional potential energy surfaces completed in hours.

By Mads Greisen H{\o}jlund, August Smart Lykke-M{\o}ller, Henry Moss, Ove Christiansen
benchmarks
More like this →
arXiv Statistics ML
Sep 25

Riemannian Gradient Descent for Gaussian Mixture Models with unknown diagonal covariances

The paper studies the numerical solution of the Beurling‑LASSO (BLASSO) for estimating Gaussian mixture models (GMMs) with unknown numbers of components and unknown diagonal covariance matrices. It introduces a Conic Particle Gradient Descent (CPGD) algorithm that incorporates Riemannian gradient descent to respect the Fisher‑Rao geometry of Gaussian distributions. The authors provide theoretical convergence guarantees, including exponential local convergence under a non‑degeneracy condition related to component separation, and demonstrate through numerical experiments that CPGD is more robust to overspecification of components than the EM algorithm.

By Romane Giard, Yohann De Castro, Roland Denis, Cl\'ement Marteau
efficiency
More like this →