pyBregMan: A Python library for Bregman Manifolds

• URL: http://arxiv.org/abs/2408.04175v1
• Date: Thu, 8 Aug 2024 02:38:19 GMT
• Title: pyBregMan: A Python library for Bregman Manifolds
• Authors: Frank Nielsen, Alexander Soen,
• Abstract summary: A Bregman manifold is a dually flat space in information geometry which admits as a canonical divergence a Bregman divergence. We describe the design of pyBregMan, a library which implements generic operations on Bregman manifold. The library also provides several core algorithms for various applications in statistics, machine learning, information fusion, and so on.
• Score: 56.880400342980394
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A Bregman manifold is a synonym for a dually flat space in information geometry which admits as a canonical divergence a Bregman divergence. Bregman manifolds are induced by smooth strictly convex functions like the cumulant or partition functions of regular exponential families, the negative entropy of mixture families, or the characteristic functions of regular cones just to list a few such convex Bregman generators. We describe the design of pyBregMan, a library which implements generic operations on Bregman manifolds and instantiate several common Bregman manifolds used in information sciences. At the core of the library is the notion of Legendre-Fenchel duality inducing a canonical pair of dual potential functions and dual Bregman divergences. The library also implements the Fisher-Rao manifolds of categorical/multinomial distributions and multivariate normal distributions. To demonstrate the use of the pyBregMan kernel manipulating those Bregman and Fisher-Rao manifolds, the library also provides several core algorithms for various applications in statistics, machine learning, information fusion, and so on.

Related papers

• Curved representational Bregman divergences and their applications [7.070726553564701]
  We show that the barycenter of a finite weighted set of parameters under a curved Bregman divergence amounts to the right Bregman projection onto the nonlinear subspace of the barycenter.<n>As an application, we report an efficient method to calculate the intersection of a finite set of $alpha$-divergence spheres.
  arXiv  Detail & Related papers  (2025-04-08T04:05:12Z)
• Semantic Gaussian Mixture Variational Autoencoder for Sequential Recommendation [49.492451800322144]
  We propose a novel VAE-based Sequential Recommendation model named SIGMA. For multi-interest elicitation, SIGMA includes a probabilistic multi-interest extraction module. Experiments on public datasets demonstrate the effectiveness of SIGMA.
  arXiv  Detail & Related papers  (2025-02-22T08:29:52Z)
• Symplectic Bregman divergences [7.070726553564701]
  Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel-Young inequality. Some potential applications of symplectic divergences in geometric mechanics, information geometry, and learning dynamics in machine learning are touched upon.
  arXiv  Detail & Related papers  (2024-08-23T10:12:08Z)
• 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. 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)
• Riemannian coordinate descent algorithms on matrix manifolds [12.05722932030768]
  We provide a general framework for developing computationally efficient coordinate descent (CD) algorithms on matrix manifold. We propose CD algorithms for various manifold such as Stiefel, Grassmann, (generalized) hyperbolic, symplectic, and symmetric positive (semi)definite. We analyze their convergence and complexity, and empirically illustrate their efficacy in several applications.
  arXiv  Detail & Related papers  (2024-06-04T11:37:11Z)
• Learning Distributions on Manifolds with Free-Form Flows [7.773439780305304]
  We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifold. M-FFF is straightforwardly adapted to any manifold with a known projection. It consistently matches or outperforms previous single-step methods.
  arXiv  Detail & Related papers  (2023-12-15T14:58:34Z)
• Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold [59.73080197971106]
  This paper presents a first-order conjugate optimization method that converges faster than the steepest descent method. It aims to achieve global convergence over the Stiefel manifold.
  arXiv  Detail & Related papers  (2023-08-21T08:02:16Z)
• Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes [10.103413548140848]
  We propose efficient Langevin Monte Carlo algorithms for sampling distributions with nonsmooth convex composite potentials. The proposed algorithms extend existing Langevin Monte Carlo algorithms in two aspects -- the ability to sample nonsmooth distributions with mirror descent-like algorithms, and the use of the more general Bregman--Moreau envelope in place of the Moreau envelope as a smooth approximation of the nonsmooth part of the potential.
  arXiv  Detail & Related papers  (2022-07-10T05:33:06Z)
• Wrapped Distributions on homogeneous Riemannian manifolds [58.720142291102135]
  Control over distributions' properties, such as parameters, symmetry and modality yield a family of flexible distributions. We empirically validate our approach by utilizing our proposed distributions within a variational autoencoder and a latent space network model.
  arXiv  Detail & Related papers  (2022-04-20T21:25:21Z)
• Generative Semantic Hashing Enhanced via Boltzmann Machines [61.688380278649056]
  Existing generative-hashing methods mostly assume a factorized form for the posterior distribution. We propose to employ the distribution of Boltzmann machine as the retrievalal posterior. We show that by effectively modeling correlations among different bits within a hash code, our model can achieve significant performance gains.
  arXiv  Detail & Related papers  (2020-06-16T01:23:39Z)
• Geomstats: A Python Package for Riemannian Geometry in Machine Learning [5.449970675406181]
  We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear equations. We provide object-oriented and extensively unit-tested implementations. We show that Geomstats provides reliable building blocks to foster research in differential geometry and statistics. The source code is freely available under the MIT license at urlgeomstats.ai.
  arXiv  Detail & Related papers  (2020-04-07T20:41:50Z)
• Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning [175.34232468746245]
  We introduce a parameterization method called Neural Bayes. It allows computing statistical quantities that are in general difficult to compute. We show two independent use cases for this parameterization.
  arXiv  Detail & Related papers  (2020-02-20T22:28:53Z)
• Particle-Gibbs Sampling For Bayesian Feature Allocation Models [77.57285768500225]
  Most widely used MCMC strategies rely on an element wise Gibbs update of the feature allocation matrix. We have developed a Gibbs sampler that can update an entire row of the feature allocation matrix in a single move. This sampler is impractical for models with a large number of features as the computational complexity scales exponentially in the number of features. We develop a Particle Gibbs sampler that targets the same distribution as the row wise Gibbs updates, but has computational complexity that only grows linearly in the number of features.
  arXiv  Detail & Related papers  (2020-01-25T22:11:51Z)

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.