paper-with-me

홈 › Papers

DBsurf: A Discrepancy Based Method for Discrete Stochastic Gradient Estimation

2023-09-07 · Pau Mulet Arabi, Alec Flowers, Lukas Mauch, Fabien Cardinaux

Computing gradients of an expectation with respect to the distributional parameters of a discrete distribution is a problem arising in many fields of science and engineering. Typically, this problem is tackled using Reinforce, which frames the problem of gradient estimation as a Monte Carlo simulation. Unfortunately, the Reinforce estimator is especially sensitive to discrepancies between the true probability distribution and the drawn samples, a common issue in low sampling regimes that results in inaccurate gradient estimates. In this paper, we introduce DBsurf, a reinforce-based estimator for discrete distributions that uses a novel sampling procedure to reduce the discrepancy between the samples and the actual distribution. To assess the performance of our estimator, we subject it to a diverse set of tasks. Among existing estimators, DBsurf attains the lowest variance in a least squares problem commonly used in the literature for benchmarking. Furthermore, DBsurf achieves the best results for training variational auto-encoders (VAE) across different datasets and sampling setups. Finally, we apply DBsurf to build a simple and efficient Neural Architecture Search (NAS) algorithm with state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:2309.03974

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingNeural Architecture Search

Similar Papers 제목 키워드 기반

Parameter Estimation in Stochastic Differential Equations via Wiener Chaos Expansion and Stochastic Gradient Descent

2026-03-27 · Francisco Delgado-Vences, José Julián Pavón-Español, Arelly Ornelas arxiv

This study addresses the inverse problem of parameter estimation for Stochastic Differential Equations (SDEs) by minimizing a regularized discrepancy functional via Stochastic Gradient Descent (SGD). To achieve computati…

Computational Efficiency

Perturbative estimation of stochastic gradients

2019-03-31 · Luca Ambrogioni, Marcel A. J. van Gerven

In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Ta…

Variational Inference

Stochastic Learning for Sparse Discrete Markov Random Fields with Controlled Gradient Approximation Error

2020-05-12 · Sinong Geng, Zhaobin Kuang, Jie Liu, Stephen Wright 외

We study the $L_1$-regularized maximum likelihood estimator/estimation (MLE) problem for discrete Markov random fields (MRFs), where efficient and scalable learning requires both sparse regularization and approximate inf…

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

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