# Expected Information Maximization: Using the I-Projection for Mixture Density Estimation

arXiv: https://arxiv.org/abs/2001.08682 · HTML: https://mlsanity.com/paper/2001.08682/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2020.

## Built on by (most cited first, 9 of 9)

- [Specializing Versatile Skill Libraries using Local Mixture of Experts](https://mlsanity.com/paper/2112.04216/) (2021)
- [A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models](https://mlsanity.com/paper/2209.11533/) (2022)
- [Non-Adversarial Imitation Learning and its Connections to Adversarial Methods](https://mlsanity.com/paper/2008.03525/) (2020)
- [Variational Distillation of Diffusion Policies into Mixture of Experts](https://mlsanity.com/paper/2406.12538/) (2024)
- [Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors](https://mlsanity.com/paper/2210.08121/) (2022)
- [Supervision Adaptation Balancing In-distribution Generalization and Out-of-distribution Detection](https://mlsanity.com/paper/2206.09380/) (2022)
- [Curriculum-Based Imitation of Versatile Skills](https://mlsanity.com/paper/2304.05171/) (2023)
- [Versatile Inverse Reinforcement Learning via Cumulative Rewards](https://mlsanity.com/paper/2111.07667/) (2021)
- [Regret-Aware Black-Box Optimization with Natural Gradients, Trust-Regions and Entropy Control](https://mlsanity.com/paper/2206.06090/) (2022)

## Abstract (arXiv)

Modelling highly multi-modal data is a challenging problem in machine learning. Most algorithms are based on maximizing the likelihood, which corresponds to the M(oment)-projection of the data distribution to the model distribution. The M-projection forces the model to average over modes it cannot represent. In contrast, the I(information)-projection ignores such modes in the data and concentrates on the modes the model can represent. Such behavior is appealing whenever we deal with highly multi-modal data where modelling single modes correctly is more important than covering all the modes. Despite this advantage, the I-projection is rarely used in practice due to the lack of algorithms that can efficiently optimize it based on data. In this work, we present a new algorithm called Expected Information Maximization (EIM) for computing the I-projection solely based on samples for general latent variable models, where we focus on Gaussian mixtures models and Gaussian mixtures of experts. Our approach applies a variational upper bound to the I-projection objective which decomposes the original objective into single objectives for each mixture component as well as for the coefficients, allowing an efficient optimization. Similar to GANs, our approach employs discriminators but uses a more stable optimization procedure, using a tight upper bound. We show that our algorithm is much more effective in computing the I-projection than recent GAN approaches and we illustrate the effectiveness of our approach for modelling multi-modal behavior on two pedestrian and traffic prediction datasets.