# DisARM: An Antithetic Gradient Estimator for Binary Latent Variables

arXiv: https://arxiv.org/abs/2006.10680 · HTML: https://mlsanity.com/paper/2006.10680/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 28 of 28)

- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [Soft Merging of Experts with Adaptive Routing](https://mlsanity.com/paper/2306.03745/) (2023)
- [Black-box Prompt Learning for Pre-trained Language Models](https://mlsanity.com/paper/2201.08531/) (2022)
- [Bridging Discrete and Backpropagation: Straight-Through and Beyond](https://mlsanity.com/paper/2304.08612/) (2023)
- [Contextual Dropout: An Efficient Sample-Dependent Dropout Module](https://mlsanity.com/paper/2103.04181/) (2021)
- [Gradient Estimation with Discrete Stein Operators](https://mlsanity.com/paper/2202.09497/) (2022)
- [Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick](https://mlsanity.com/paper/2311.12569/) (2023)
- [Storchastic: A Framework for General Stochastic Automatic Differentiation](https://mlsanity.com/paper/2104.00428/) (2021)
- [ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables](https://mlsanity.com/paper/2105.14141/) (2021)
- [Coupled Gradient Estimators for Discrete Latent Variables](https://mlsanity.com/paper/2106.08056/) (2021)
- [Double Control Variates for Gradient Estimation in Discrete Latent Variable Models](https://mlsanity.com/paper/2111.05300/) (2021)
- [Training Discrete Deep Generative Models via Gapped Straight-Through Estimator](https://mlsanity.com/paper/2206.07235/) (2022)
- [Gradient Estimation for Binary Latent Variables via Gradient Variance Clipping](https://mlsanity.com/paper/2208.06124/) (2022)
- [Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation](https://mlsanity.com/paper/2312.15901/) (2023)
- [CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator](https://mlsanity.com/paper/2110.14002/) (2021)
- [A Lower Bound of Hash Codes' Performance](https://mlsanity.com/paper/2210.05899/) (2022)
- [Efficient compression of neural networks and datasets](https://mlsanity.com/paper/2505.17469/) (2025)
- [Rao-Blackwellised Reparameterisation Gradients](https://mlsanity.com/paper/2506.07687/) (2025)
- [Hindsight Network Credit Assignment: Efficient Credit Assignment in Networks of Discrete Stochastic Units](https://mlsanity.com/paper/2110.07700/) (2021)
- [DBsurf: A Discrepancy Based Method for Discrete Stochastic Gradient Estimation](https://mlsanity.com/paper/2309.03974/) (2023)
- [Nonparametric Discrete Choice Experiments with Machine Learning Guided Adaptive Design](https://mlsanity.com/paper/2310.12026/) (2023)
- [What to Do When Your Discrete Optimization Is the Size of a Neural Network?](https://mlsanity.com/paper/2402.10339/) (2024)
- [Probabilistic and nonlinear compressive sensing](https://mlsanity.com/paper/2509.15060/) (2025)
- [Unbiased Single-Queried Gradient for Combinatorial Objective](https://mlsanity.com/paper/2602.05119/) (2026)
- [Weave of Formal Thought](https://mlsanity.com/paper/2606.25987/) (2026)
- [GradInf: Gradient Estimation as Probabilistic Inference](https://mlsanity.com/paper/2607.07840/) (2026)
- [Active Data Acquisition with Side Information via Discrete Diffusion Priors](https://mlsanity.com/paper/2609.32252/) (2026)
- [Variance-Optimal Control Variates for Learning with Black-box Feedback](https://mlsanity.com/paper/2610.04766/) (2026)

## Abstract (arXiv)

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 the system, which are not always available or even possible. The Augment-REINFORCE-Merge (ARM) estimator provides an alternative that, instead of relaxation, uses continuous augmentation. Applying antithetic sampling over the augmenting variables yields a relatively low-variance and unbiased estimator applicable to any model with binary latent variables. However, while antithetic sampling reduces variance, the augmentation process increases variance. We show that ARM can be improved by analytically integrating out the randomness introduced by the augmentation process, guaranteeing substantial variance reduction. Our estimator, DisARM, is simple to implement and has the same computational cost as ARM. We evaluate DisARM on several generative modeling benchmarks and show that it consistently outperforms ARM and a strong independent sample baseline in terms of both variance and log-likelihood. Furthermore, we propose a local version of DisARM designed for optimizing the multi-sample variational bound, and show that it outperforms VIMCO, the current state-of-the-art method.