Probabilistic Integral Circuits

• URL: http://arxiv.org/abs/2310.16986v1
• Date: Wed, 25 Oct 2023 20:38:18 GMT
• Title: Probabilistic Integral Circuits
• Authors: Gennaro Gala, Cassio de Campos, Robert Peharz, Antonio Vergari, Erik Quaeghebeur
• Abstract summary: We introduce a new language of computational graphs that extends PCs with integral units representing continuous LVs. In practice, we parameterise PICs with light-weight neural nets delivering an intractable hierarchical continuous mixture. We show that such PIC-approximating PCs systematically outperform PCs commonly learned via expectation-maximization or SGD.
• Score: 11.112802758446344
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Continuous latent variables (LVs) are a key ingredient of many generative models, as they allow modelling expressive mixtures with an uncountable number of components. In contrast, probabilistic circuits (PCs) are hierarchical discrete mixtures represented as computational graphs composed of input, sum and product units. Unlike continuous LV models, PCs provide tractable inference but are limited to discrete LVs with categorical (i.e. unordered) states. We bridge these model classes by introducing probabilistic integral circuits (PICs), a new language of computational graphs that extends PCs with integral units representing continuous LVs. In the first place, PICs are symbolic computational graphs and are fully tractable in simple cases where analytical integration is possible. In practice, we parameterise PICs with light-weight neural nets delivering an intractable hierarchical continuous mixture that can be approximated arbitrarily well with large PCs using numerical quadrature. On several distribution estimation benchmarks, we show that such PIC-approximating PCs systematically outperform PCs commonly learned via expectation-maximization or SGD.

Related papers

• Sum of Squares Circuits [8.323409122604893]
  Probabilistic circuits (PCs) offer a framework where this tractability-vs-expressiveness trade-off can be analyzed theoretically. We show that squared PCs encoding subtractive mixtures via negative parameters can be exponentially more expressive than monotonic PCs. We formalize a novel class of PCs -- sum of squares PCs -- that can be exponentially more expressive than both squared and monotonic PCs.
  arXiv  Detail & Related papers  (2024-08-21T17:08:05Z)
• Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits [5.969243233796684]
  Probabilistic integral circuits (PICs) are symbolic computational graphs defining continuous latent variables (LVs) PICs are tractable if LVs can be analytically integrated out, otherwise they can be approximated by tractable probabilistic circuits (PC) We present a pipeline for building DAG-shaped PICs out of arbitrary variable decompositions, a procedure for training PICs using tensorized circuit architectures, and neural functional sharing techniques.
  arXiv  Detail & Related papers  (2024-06-10T17:30:17Z)
• Continuous Mixtures of Tractable Probabilistic Models [10.667104977730304]
  Probabilistic models based on continuous latent spaces, such as variational autoencoders, can be understood as uncountable mixture models. Probabilistic circuits (PCs) can be understood as hierarchical discrete mixture models. In this paper, we investigate a hybrid approach, namely continuous mixtures of tractable models with a small latent dimension.
  arXiv  Detail & Related papers  (2022-09-21T18:18:32Z)
• Low-Rank Constraints for Fast Inference in Structured Models [110.38427965904266]
  This work demonstrates a simple approach to reduce the computational and memory complexity of a large class of structured models. Experiments with neural parameterized structured models for language modeling, polyphonic music modeling, unsupervised grammar induction, and video modeling show that our approach matches the accuracy of standard models at large state spaces.
  arXiv  Detail & Related papers  (2022-01-08T00:47:50Z)
• HyperSPNs: Compact and Expressive Probabilistic Circuits [89.897635970366]
  HyperSPNs is a new paradigm of generating the mixture weights of large PCs using a small-scale neural network. We show the merits of our regularization strategy on two state-of-the-art PC families introduced in recent literature.
  arXiv  Detail & Related papers  (2021-12-02T01:24:43Z)
• Probabilistic Generating Circuits [50.98473654244851]
  We propose probabilistic generating circuits (PGCs) for their efficient representation. PGCs are not just a theoretical framework that unifies vastly different existing models, but also show huge potential in modeling realistic data. We exhibit a simple class of PGCs that are not trivially subsumed by simple combinations of PCs and DPPs, and obtain competitive performance on a suite of density estimation benchmarks.
  arXiv  Detail & Related papers  (2021-02-19T07:06:53Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)
• Continuous-in-Depth Neural Networks [107.47887213490134]
  We first show that ResNets fail to be meaningful dynamical in this richer sense. We then demonstrate that neural network models can learn to represent continuous dynamical systems. We introduce ContinuousNet as a continuous-in-depth generalization of ResNet architectures.
  arXiv  Detail & Related papers  (2020-08-05T22:54:09Z)
• Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits [99.59941892183454]
  We propose Einsum Networks (EiNets), a novel implementation design for PCs. At their core, EiNets combine a large number of arithmetic operations in a single monolithic einsum-operation. We show that the implementation of Expectation-Maximization (EM) can be simplified for PCs, by leveraging automatic differentiation.
  arXiv  Detail & Related papers  (2020-04-13T23:09:15Z)

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.