← Back to all news
arXiv Machine Learning By Pascal Mattia Esser, Frank Nielsen

Characterizing Learning Dynamics under Relative Reparameterization of Singular Models

Read the original on arXiv Machine Learning →

arXiv:2206. 08598v2 Announce Type: replace Abstract: A common way to analyze learning of statistical models is to consider operations in the models parameter space, however this becomes challenging when there is no one-to-one mapping between the parameter space and the underlying statistical model space.

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 Machine Learning.

Related stories

arXiv Machine Learning
Aug 21

Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models

arXiv:2608. 20183v1 Announce Type: new Abstract: Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect model selection in settings such as deep learning.

By Gr\'egoire Sergeant-Perthuis (CQSB, Sorbonne Universit\'e), Elias Tsigaridas (Ouragan Team, INRIA), Jules Tsukahara (Ouragan Team, INRIA)
More like this →
arXiv Machine Learning
Jun 5

Dead Directions: Geometric Singular Learning

arXiv:2606. 05957v1 Announce Type: new Abstract: Singular learning theory and information geometry have studied the same parameter spaces in mostly separate vocabularies: the former computes Bayesian invariants in resolved coordinates, the latter works in original coordinates under a non-degeneracy assumption that overparameterised models routinely violate.

By Tejas Pradeep Shirodkar
More like this →
arXiv Machine Learning
Aug 19

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures

arXiv:2506. 06584v2 Announce Type: replace Abstract: Learning Gaussian Mixture Models (GMMs) is a fundamental problem in statistics and machine learning, with the Expectation-Maximization (EM) algorithm and its popular variant gradient EM being arguably the most widely used algorithms in practice.

By Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du
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 →