paper-with-me

홈 › Papers

Estimating Gradients for Discrete Random Variables by Sampling without Replacement

2020-02-14 · ICLR 2020 1 · Wouter Kool, Herke van Hoof, Max Welling

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.

📄 PDF Abstract BibTeX arXiv:2002.06043

Code (1)

wouterkool/estimating-gradients-without-replacement 공식 구현 pytorch

Tasks

Structured Prediction

Methods 이 논문이 사용한 방법론

REINFORCE REINFORCE is a Monte Carlo variant of a policy gradient algorithm in reinforcement learning. The agent collects samples of an episode using its current policy, and uses it to…

Similar Papers 제목 키워드 기반

Local Expectation Gradients for Black Box Variational Inference

2015-12-01 · NeurIPS 2015 12 · Michalis Titsias Rc Aueb, Miguel Lázaro-Gredilla

We introduce local expectation gradients which is a general purpose stochastic variational inference algorithm for constructing stochastic gradients by sampling from the variational distribution. This algorithm divides t…

Variational Inference

Local Expectation Gradients for Doubly Stochastic Variational Inference

2015-03-04 · Michalis K. Titsias

We introduce local expectation gradients which is a general purpose stochastic variational inference algorithm for constructing stochastic gradients through sampling from the variational distribution. This algorithm divi…

Variational Inference

Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables

2020-03-04 · Weonyoung Joo, Dongjun Kim, Seungjae Shin, Il-Chul Moon

Estimating the gradients of stochastic nodes in stochastic computational graphs is one of the crucial research questions in the deep generative modeling community, which enables the gradient descent optimization on neura…

Topic Models

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

2016-11-02 · Chris J. Maddison, andriy mnih, Yee Whye Teh

The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameter…

Density EstimationStructured Prediction

DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

2020-06-18 · NeurIPS 2020 12 · Zhe Dong, andriy mnih, George Tucker

Training models with discrete latent variables is challenging due to the difficulty of estimating the gradients accurately. Much of the recent progress has been achieved by taking advantage of continuous relaxations of t…