Interpolating between sampling and variational inference with infinite stochastic mixtures

• URL: http://arxiv.org/abs/2110.09618v1
• Date: Mon, 18 Oct 2021 20:50:06 GMT
• Title: Interpolating between sampling and variational inference with infinite stochastic mixtures
• Authors: Richard D. Lange, Ari Benjamin, Ralf M. Haefner, Xaq Pitkow
• Abstract summary: Sampling and Variational Inference (VI) are two large families of methods for approximate inference with complementary strengths. Here, we develop a framework for constructing intermediate algorithms that balance the strengths of both sampling and VI. This work is a first step towards a highly flexible yet simple family of inference methods that combines the complementary strengths of sampling and VI.
• Score: 6.021787236982659
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling and Variational Inference (VI) are two large families of methods for approximate inference with complementary strengths. Sampling methods excel at approximating arbitrary probability distributions, but can be inefficient. VI methods are efficient, but can fail when probability distributions are complex. Here, we develop a framework for constructing intermediate algorithms that balance the strengths of both sampling and VI. Both approximate a probability distribution using a mixture of simple component distributions: in sampling, each component is a delta-function and is chosen stochastically, while in standard VI a single component is chosen to minimize divergence. We show that sampling and VI emerge as special cases of an optimization problem over a mixing distribution, and intermediate approximations arise by varying a single parameter. We then derive closed-form sampling dynamics over variational parameters that stochastically build a mixture. Finally, we discuss how to select the optimal compromise between sampling and VI given a computational budget. This work is a first step towards a highly flexible yet simple family of inference methods that combines the complementary strengths of sampling and VI.

Related papers

• Particle Semi-Implicit Variational Inference [2.555222031881788]
  Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution. Existing SIVI methods parameterize the mixing distribution using implicit distributions, leading to intractable variational densities. We propose a novel method for SIVI called Particle Variational Inference (PVI) which employs empirical measures to approximate the optimal mixing distributions.
  arXiv  Detail & Related papers  (2024-06-30T10:21:41Z)
• Weak Generative Sampler to Efficiently Sample Invariant Distribution of Stochastic Differential Equation [8.67581853745823]
  Current deep learning-based method solves the stationary Fokker--Planck equation to determine the invariant probability density function in form of deep neural networks. We introduce a framework that employs a weak generative sampler (WGS) to directly generate independent and identically distributed (iid) samples. Our proposed loss function is based on the weak form of the Fokker--Planck equation, integrating normalizing flows to characterize the invariant distribution.
  arXiv  Detail & Related papers  (2024-05-29T16:41:42Z)
• Equivariant Flow Matching with Hybrid Probability Transport [69.11915545210393]
  Diffusion Models (DMs) have demonstrated effectiveness in generating feature-rich geometries. DMs typically suffer from unstable probability dynamics with inefficient sampling speed. We introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics.
  arXiv  Detail & Related papers  (2023-12-12T11:13:13Z)
• Robust scalable initialization for Bayesian variational inference with multi-modal Laplace approximations [0.0]
  Variational mixtures with full-covariance structures suffer from a quadratic growth due to variational parameters with the number of parameters. We propose a method for constructing an initial Gaussian model approximation that can be used to warm-start variational inference.
  arXiv  Detail & Related papers  (2023-07-12T19:30:04Z)
• Unsupervised Learning of Sampling Distributions for Particle Filters [80.6716888175925]
  We put forward four methods for learning sampling distributions from observed measurements. Experiments demonstrate that learned sampling distributions exhibit better performance than designed, minimum-degeneracy sampling distributions.
  arXiv  Detail & Related papers  (2023-02-02T15:50:21Z)
• Comparing two samples through stochastic dominance: a graphical approach [2.867517731896504]
  Non-deterministic measurements are common in real-world scenarios. We propose an alternative framework to visually compare two samples according to their estimated cumulative distribution functions.
  arXiv  Detail & Related papers  (2022-03-15T13:37:03Z)
• Density Ratio Estimation via Infinitesimal Classification [85.08255198145304]
  We propose DRE-infty, a divide-and-conquer approach to reduce Density ratio estimation (DRE) to a series of easier subproblems. Inspired by Monte Carlo methods, we smoothly interpolate between the two distributions via an infinite continuum of intermediate bridge distributions. We show that our approach performs well on downstream tasks such as mutual information estimation and energy-based modeling on complex, high-dimensional datasets.
  arXiv  Detail & Related papers  (2021-11-22T06:26:29Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• Sparse Communication via Mixed Distributions [29.170302047339174]
  We build theoretical foundations for "mixed random variables" Our framework suggests two strategies for representing and sampling mixed random variables. We experiment with both approaches on an emergent communication benchmark.
  arXiv  Detail & Related papers  (2021-08-05T14:49:03Z)
• A One-step Approach to Covariate Shift Adaptation [82.01909503235385]
  A default assumption in many machine learning scenarios is that the training and test samples are drawn from the same probability distribution. We propose a novel one-step approach that jointly learns the predictive model and the associated weights in one optimization.
  arXiv  Detail & Related papers  (2020-07-08T11:35:47Z)
• Distributed, partially collapsed MCMC for Bayesian Nonparametrics [68.5279360794418]
  We exploit the fact that completely random measures, which commonly used models like the Dirichlet process and the beta-Bernoulli process can be expressed as, are decomposable into independent sub-measures. We use this decomposition to partition the latent measure into a finite measure containing only instantiated components, and an infinite measure containing all other components. The resulting hybrid algorithm can be applied to allow scalable inference without sacrificing convergence guarantees.
  arXiv  Detail & Related papers  (2020-01-15T23:10:13Z)

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.