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

Abstract

Current meta-learning approaches focus on learning functional representations of relationships between variables, \textit{i.e.} estimating conditional expectations in regression. In many applications, however, the conditional distributions cannot be meaningfully summarized solely by expectation (due to \textit{e.g.} multimodality). We introduce a novel technique for meta-learning conditional densities, which combines neural representation and noise contrastive estimation together with well-established literature in conditional mean embeddings into reproducing kernel Hilbert spaces. The method shows significant improvements over standard density estimation methods on synthetic and real-world data, by leveraging shared representations across multiple conditional density estimation tasks.

Cite

Text

Ton et al. "Noise Contrastive Meta-Learning for Conditional Density Estimation Using Kernel Mean Embeddings." Artificial Intelligence and Statistics, 2021.

Markdown

[Ton et al. "Noise Contrastive Meta-Learning for Conditional Density Estimation Using Kernel Mean Embeddings." Artificial Intelligence and Statistics, 2021.](https://mlanthology.org/aistats/2021/ton2021aistats-noise/)

BibTeX

@inproceedings{ton2021aistats-noise,
  title     = {{Noise Contrastive Meta-Learning for Conditional Density Estimation Using Kernel Mean Embeddings}},
  author    = {Ton, Jean-Francois and Chan, Lucian and Whye Teh, Yee and Sejdinovic, Dino},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2021},
  pages     = {1099-1107},
  volume    = {130},
  url       = {https://mlanthology.org/aistats/2021/ton2021aistats-noise/}
}