# Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings

arXiv: https://arxiv.org/abs/1906.02236 · HTML: https://mlsanity.com/paper/1906.02236/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 10 of 10)

- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Conditional Contrastive Learning with Kernel](https://mlsanity.com/paper/2202.05458/) (2022)
- [BayesIMP: Uncertainty Quantification for Causal Data Fusion](https://mlsanity.com/paper/2106.03477/) (2021)
- [Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data](https://mlsanity.com/paper/2106.07636/) (2021)
- [On Contrastive Representations of Stochastic Processes](https://mlsanity.com/paper/2106.10052/) (2021)
- [Contrastive Conditional Neural Processes](https://mlsanity.com/paper/2203.03978/) (2022)
- [Learning to Embed Distributions via Maximum Kernel Entropy](https://mlsanity.com/paper/2408.00549/) (2024)
- [Adversarially Contrastive Estimation of Conditional Neural Processes](https://mlsanity.com/paper/2303.13004/) (2023)
- [Returning The Favour: When Regression Benefits From Probabilistic Causal Knowledge](https://mlsanity.com/paper/2301.11214/) (2023)
- [Adaptive Kernel Density Estimation with Pre-training](https://mlsanity.com/paper/2605.13092/) (2026)

## Abstract (arXiv)

Current meta-learning approaches focus on learning functional representations of relationships between variables, i.e. on estimating conditional expectations in regression. In many applications, however, we are faced with conditional distributions which cannot be meaningfully summarized using expectation only (due to e.g. multimodality). Hence, we consider the problem of conditional density estimation in the meta-learning setting. We introduce a novel technique for meta-learning which combines neural representation and noise-contrastive estimation with the established literature of conditional mean embeddings into reproducing kernel Hilbert spaces. The method is validated on synthetic and real-world problems, demonstrating the utility of sharing learned representations across multiple conditional density estimation tasks.