Gradient Estimation with Discrete Stein Operators

• URL: http://arxiv.org/abs/2202.09497v8
• Date: Sun, 14 Apr 2024 17:08:45 GMT
• Title: Gradient Estimation with Discrete Stein Operators
• Authors: Jiaxin Shi, Yuhao Zhou, Jessica Hwang, Michalis K. Titsias, Lester Mackey,
• Abstract summary: 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.
• Score: 44.64146470394269
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gradient estimation -- approximating the gradient of an expectation with respect to the parameters of a distribution -- is central to the solution of many machine learning problems. However, when the distribution is discrete, most common gradient estimators suffer from excessive variance. To improve the quality of gradient estimation, we introduce a variance reduction technique based on Stein operators for discrete distributions. We then use this technique to build flexible control variates for the REINFORCE leave-one-out estimator. Our control variates can be adapted online to minimize variance and do not require extra evaluations of the target function. In benchmark generative modeling tasks such as training binary variational autoencoders, our gradient estimator achieves substantially lower variance than state-of-the-art estimators with the same number of function evaluations.

Related papers

• Revisiting Score Function Estimators for $k$-Subset Sampling [5.464421236280698]
  We show how to efficiently compute the $k$-subset distribution's score function using a discrete Fourier transform. The resulting estimator provides both exact samples and unbiased gradient estimates. Experiments in feature selection show results competitive with current methods, despite weaker assumptions.
  arXiv  Detail & Related papers  (2024-07-22T21:26:39Z)
• Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning [55.75959755058356]
  In deep reinforcement learning, estimating the value function is essential to evaluate the quality of states and actions. A recent study suggested that the error distribution for training the value function is often skewed because of the properties of the Bellman operator. We proposed a method called Symmetric Q-learning, in which the synthetic noise generated from a zero-mean distribution is added to the target values to generate a Gaussian error distribution.
  arXiv  Detail & Related papers  (2024-03-12T14:49:19Z)
• Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models [28.011868604717726]
  We present Adaptive IMLE, the first adaptive gradient estimator for complex discrete distributions. We show that our estimator can produce faithful estimates while requiring orders of magnitude fewer samples than other gradient estimators.
  arXiv  Detail & Related papers  (2022-09-11T13:32:39Z)
• Training Discrete Deep Generative Models via Gapped Straight-Through Estimator [72.71398034617607]
  We propose a Gapped Straight-Through ( GST) estimator to reduce the variance without incurring resampling overhead. This estimator is inspired by the essential properties of Straight-Through Gumbel-Softmax. Experiments demonstrate that the proposed GST estimator enjoys better performance compared to strong baselines on two discrete deep generative modeling tasks.
  arXiv  Detail & Related papers  (2022-06-15T01:46:05Z)
• Double Control Variates for Gradient Estimation in Discrete Latent Variable Models [32.33171301923846]
  We introduce a variance reduction technique for score function estimators. We show that our estimator can have lower variance compared to other state-of-the-art estimators.
  arXiv  Detail & Related papers  (2021-11-09T18:02:42Z)
• Storchastic: A Framework for General Stochastic Automatic Differentiation [9.34612743192798]
  We introduce Storchastic, a new framework for automatic differentiation of graphs. Storchastic allows the modeler to choose from a wide variety of gradient estimation methods at each sampling step. Storchastic is provably unbiased for estimation of any-order gradients, and generalizes variance reduction techniques to higher-order gradient estimates.
  arXiv  Detail & Related papers  (2021-04-01T12:19:54Z)
• Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator [93.05919133288161]
  We show that the variance of the straight-through variant of the popular Gumbel-Softmax estimator can be reduced through Rao-Blackwellization. This provably reduces the mean squared error. We empirically demonstrate that this leads to variance reduction, faster convergence, and generally improved performance in two unsupervised latent variable models.
  arXiv  Detail & Related papers  (2020-10-09T22:54:38Z)
• 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)
• Estimating Gradients for Discrete Random Variables by Sampling without Replacement [93.09326095997336]
  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.
  arXiv  Detail & Related papers  (2020-02-14T14:15:18Z)

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.