# Controllable Missingness from Uncontrollable Missingness: Joint Learning Measurement Policy and Imputation

arXiv: https://arxiv.org/abs/2204.03872 · HTML: https://mlsanity.com/paper/2204.03872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 10 of 10)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [An Introduction to Deep Reinforcement Learning](https://mlsanity.com/paper/1811.12560/) (2018)
- [Virtual to Real Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1704.03952/) (2017)
- [MisGAN: Learning from Incomplete Data with Generative Adversarial Networks](https://mlsanity.com/paper/1902.09599/) (2019)
- [Learning When and Where to Zoom with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00425/) (2020)
- [Flexible High-Dimensional Unsupervised Learning with Missing Data](https://mlsanity.com/paper/1706.06185/) (2017)

## Abstract (arXiv)

Due to the cost or interference of measurement, we need to control measurement system. Assuming that each variable can be measured sequentially, there exists optimal policy choosing next measurement for the former observations. Though optimal measurement policy is actually dependent on the goal of measurement, we mainly focus on retrieving complete data, so called as imputation. Also, we adapt the imputation method to missingness varying with measurement policy. However, learning measurement policy and imputation requires complete data which is impossible to be observed, unfortunately. To tackle this problem, we propose a data generation method and joint learning algorithm. The main idea is that 1) the data generation method is inherited by imputation method, and 2) the adaptation of imputation encourages measurement policy to learn more than individual learning. We implemented some variations of proposed algorithm for two different datasets and various missing rates. From the experimental results, we demonstrate that our algorithm is generally applicable and outperforms baseline methods.