Minimizing $f$-Divergences by Interpolating Velocity Fields

• URL: http://arxiv.org/abs/2305.15577v3
• Date: Thu, 6 Jun 2024 13:31:45 GMT
• Title: Minimizing $f$-Divergences by Interpolating Velocity Fields
• Authors: Song Liu, Jiahao Yu, Jack Simons, Mingxuan Yi, Mark Beaumont,
• Abstract summary: Wasserstein Gradient Flow can move particles along a path that minimizes the $f$-divergence between the target and particle distributions. To move particles, we need to calculate the corresponding velocity fields derived from a density ratio function between these two distributions.
• Score: 6.8979561422924185
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many machine learning problems can be seen as approximating a \textit{target} distribution using a \textit{particle} distribution by minimizing their statistical discrepancy. Wasserstein Gradient Flow can move particles along a path that minimizes the $f$-divergence between the target and particle distributions. To move particles, we need to calculate the corresponding velocity fields derived from a density ratio function between these two distributions. Previous works estimated such density ratio functions and then differentiated the estimated ratios. These approaches may suffer from overfitting, leading to a less accurate estimate of the velocity fields. Inspired by non-parametric curve fitting, we directly estimate these velocity fields using interpolation techniques. We prove that our estimators are consistent under mild conditions. We validate their effectiveness using novel applications on domain adaptation and missing data imputation.

Related papers

• Kinetic Interacting Particle Langevin Monte Carlo [0.0]
  This paper introduces and analyses interacting underdamped Langevin algorithms, for statistical inference in latent variable models. We propose a diffusion process that evolves jointly in the space of parameters and latent variables. We provide two explicit discretisations of this diffusion as practical algorithms to estimate parameters of statistical models.
  arXiv  Detail & Related papers  (2024-07-08T09:52:46Z)
• Noise-Free Sampling Algorithms via Regularized Wasserstein Proximals [3.4240632942024685]
  We consider the problem of sampling from a distribution governed by a potential function. This work proposes an explicit score based MCMC method that is deterministic, resulting in a deterministic evolution for particles.
  arXiv  Detail & Related papers  (2023-08-28T23:51:33Z)
• Training normalizing flows with computationally intensive target probability distributions [0.018416014644193065]
  We propose an estimator for normalizing flows based on the REINFORCE algorithm. It is up to ten times faster in terms of the wall-clock time and requires up to $30%$ less memory.
  arXiv  Detail & Related papers  (2023-08-25T10:40:46Z)
• Statistical Efficiency of Score Matching: The View from Isoperimetry [96.65637602827942]
  We show a tight connection between statistical efficiency of score matching and the isoperimetric properties of the distribution being estimated. We formalize these results both in the sample regime and in the finite regime.
  arXiv  Detail & Related papers  (2022-10-03T06:09:01Z)
• Learning Optimal Flows for Non-Equilibrium Importance Sampling [13.469239537683299]
  We develop a method to perform calculations based on generating samples from a simple base distribution, transporting them along the flow generated by a velocity field, and performing averages along these flowlines. On the theory side we discuss how to tailor the velocity field to the target and establish general conditions under which the proposed estimator is a perfect estimator. On the computational side we show how to use deep learning to represent the velocity field by a neural network and train it towards the zero variance optimum.
  arXiv  Detail & Related papers  (2022-06-20T17:25:26Z)
• Efficient CDF Approximations for Normalizing Flows [64.60846767084877]
  We build upon the diffeomorphic properties of normalizing flows to estimate the cumulative distribution function (CDF) over a closed region. Our experiments on popular flow architectures and UCI datasets show a marked improvement in sample efficiency as compared to traditional estimators.
  arXiv  Detail & Related papers  (2022-02-23T06:11:49Z)
• Near-optimal estimation of smooth transport maps with kernel sums-of-squares [81.02564078640275]
  Under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds. The object of interest for applications such as generative modeling is the underlying optimal transport map. We propose the first tractable algorithm for which the statistical $L2$ error on the maps nearly matches the existing minimax lower-bounds for smooth map estimation.
  arXiv  Detail & Related papers  (2021-12-03T13:45:36Z)
• 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)
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization [106.70006655990176]
  A distributional optimization problem arises widely in machine learning and statistics. We propose a novel particle-based algorithm, dubbed as variational transport, which approximately performs Wasserstein gradient descent. We prove that when the objective function satisfies a functional version of the Polyak-Lojasiewicz (PL) (Polyak, 1963) and smoothness conditions, variational transport converges linearly.
  arXiv  Detail & Related papers  (2020-12-21T18:33:13Z)
• Minimax Optimal Estimation of KL Divergence for Continuous Distributions [56.29748742084386]
  Esting Kullback-Leibler divergence from identical and independently distributed samples is an important problem in various domains. One simple and effective estimator is based on the k nearest neighbor between these samples.
  arXiv  Detail & Related papers  (2020-02-26T16:37:37Z)

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.