paper-with-me

Papers

Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference

2018-10-05 · Mike Wu, Noah Goodman, Stefano Ermon

Stochastic optimization techniques are standard in variational inference algorithms. These methods estimate gradients by approximating expectations with independent Monte Carlo samples. In this paper, we explore a technique that uses correlated, but more representative , samples to reduce estimator variance. Specifically, we show how to generate antithetic samples that match sample moments with the true moments of an underlying importance distribution. Combining a differentiable antithetic sampler with modern stochastic variational inference, we showcase the effectiveness of this approach for learning a deep generative model.

📄 PDF Abstract BibTeX arXiv:1810.02555

Code (1)

mhw32/antithetic-vae-public 공식 구현 pytorch

Tasks

Stochastic OptimizationVariational Inference

Similar Papers 제목 키워드 기반

Accelerating Stochastic Gradient Descent Using Antithetic Sampling

2018-10-07 · Jingchang Liu, Linli Xu

(Mini-batch) Stochastic Gradient Descent is a popular optimization method which has been applied to many machine learning applications. But a rather high variance introduced by the stochastic gradient in each step may sl…

Binary ClassificationGeneral Classification

Stochastic Variational Optimization

2018-09-13 · Thomas Bird, Julius Kunze, David Barber

Variational Optimization forms a differentiable upper bound on an objective. We show that approaches such as Natural Evolution Strategies and Gaussian Perturbation, are special cases of Variational Optimization in which …

ARM: Augment-REINFORCE-Merge Gradient for Stochastic Binary Networks

2018-07-30 · ICLR 2019 5 · Mingzhang Yin, Mingyuan Zhou

To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable a…

Data AugmentationVariational Inference

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…

Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging

2026-03-23 · Dongxia Wu, Yuhui Zhang, Serena Yeung-Levy, Emma Lundberg 외 arxiv

Distribution-to-distribution generative models support scientific imaging tasks ranging from modeling cellular perturbation responses to translating medical images across conditions. Trustworthy generation requires relia…