Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings
This addresses the need for handling complex conditional distributions, such as multimodality, in meta-learning applications, representing an incremental advancement over existing methods.
The paper tackled the problem of conditional density estimation in meta-learning, where existing methods focus on conditional expectations, by introducing a novel technique combining neural representation, noise-contrastive estimation, and kernel mean embeddings, and demonstrated its utility on synthetic and real-world tasks.
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.