Estimating Gradients for Discrete Random Variables by Sampling without Replacement

• URL: http://arxiv.org/abs/2002.06043v1
• Date: Fri, 14 Feb 2020 14:15:18 GMT
• Title: Estimating Gradients for Discrete Random Variables by Sampling without Replacement
• Authors: Wouter Kool, Herke van Hoof, Max Welling
• Abstract summary: We derive an unbiased estimator for expectations over discrete random variables based on sampling without replacement. We show that our estimator can be derived as the Rao-Blackwellization of three different estimators.
• Score: 93.09326095997336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We derive an unbiased estimator for expectations over discrete random variables based on sampling without replacement, which reduces variance as it avoids duplicate samples. We show that our estimator can be derived as the Rao-Blackwellization of three different estimators. Combining our estimator with REINFORCE, we obtain a policy gradient estimator and we reduce its variance using a built-in control variate which is obtained without additional model evaluations. The resulting estimator is closely related to other gradient estimators. Experiments with a toy problem, a categorical Variational Auto-Encoder and a structured prediction problem show that our estimator is the only estimator that is consistently among the best estimators in both high and low entropy settings.

Related papers

• Multivariate root-n-consistent smoothing parameter free matching estimators and estimators of inverse density weighted expectations [51.000851088730684]
  We develop novel modifications of nearest-neighbor and matching estimators which converge at the parametric $sqrt n $-rate. We stress that our estimators do not involve nonparametric function estimators and in particular do not rely on sample-size dependent parameters smoothing.
  arXiv  Detail & Related papers  (2024-07-11T13:28:34Z)
• Statistical Barriers to Affine-equivariant Estimation [10.077727846124633]
  We investigate the quantitative performance of affine-equivariant estimators for robust mean estimation. We find that classical estimators are either quantitatively sub-optimal or lack any quantitative guarantees. We construct a new affine-equivariant estimator which nearly matches our lower bound.
  arXiv  Detail & Related papers  (2023-10-16T18:42:00Z)
• Gradient Estimation with Discrete Stein Operators [44.64146470394269]
  We introduce a variance reduction technique based on Stein operators for discrete distributions. Our technique achieves substantially lower variance than state-of-the-art estimators with the same number of function evaluations.
  arXiv  Detail & Related papers  (2022-02-19T02:22:23Z)
• CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator [60.799183326613395]
  We propose an unbiased estimator for categorical random variables based on multiple mutually negatively correlated (jointly antithetic) samples. CARMS combines REINFORCE with copula based sampling to avoid duplicate samples and reduce its variance, while keeping the estimator unbiased using importance sampling. We evaluate CARMS on several benchmark datasets on a generative modeling task, as well as a structured output prediction task, and find it to outperform competing methods including a strong self-control baseline.
  arXiv  Detail & Related papers  (2021-10-26T20:14:30Z)
• Nonparametric Score Estimators [49.42469547970041]
  Estimating the score from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models. We provide a unifying view of these estimators under the framework of regularized nonparametric regression. We propose score estimators based on iterative regularization that enjoy computational benefits from curl-free kernels and fast convergence.
  arXiv  Detail & Related papers  (2020-05-20T15:01:03Z)
• Nonparametric Estimation of the Fisher Information and Its Applications [82.00720226775964]
  This paper considers the problem of estimation of the Fisher information for location from a random sample of size $n$. An estimator proposed by Bhattacharya is revisited and improved convergence rates are derived. A new estimator, termed a clipped estimator, is proposed.
  arXiv  Detail & Related papers  (2020-05-07T17:21:56Z)
• SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models [80.22609163316459]
  We introduce an unbiased estimator of the log marginal likelihood and its gradients for latent variable models based on randomized truncation of infinite series. We show that models trained using our estimator give better test-set likelihoods than a standard importance-sampling based approach for the same average computational cost.
  arXiv  Detail & Related papers  (2020-04-01T11:49:30Z)

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.