# Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference

arXiv: https://arxiv.org/abs/1810.02555 · HTML: https://mlsanity.com/paper/1810.02555/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2018.

## Built on by (most cited first, 4 of 4)

- [ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables](https://mlsanity.com/paper/2105.14141/) (2021)
- [Partition Function Estimation: A Quantitative Study](https://mlsanity.com/paper/2105.11132/) (2021)
- [Uphill Roads to Variational Tightness: Monotonicity and Monte Carlo Objectives](https://mlsanity.com/paper/2201.10989/) (2022)
- [RAMPAGE: RAndomized Mid-Point for debiAsed Gradient Extrapolation](https://mlsanity.com/paper/2603.22155/) (2026)

## Abstract (arXiv)

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.