Sparse Gaussian Neural Processes
This addresses the problem of high computational cost and poor interpretability for practitioners in meta-learning, offering a solution that is particularly beneficial when tasks have many observations or when expert domain knowledge is available.
The paper tackles the computational inefficiency and lack of interpretability in deep learning models for probabilistic meta-learning by introducing a family of models that meta-learn sparse Gaussian process inference, enabling rapid prediction on new tasks and allowing manual elicitation of priors in neural processes for the first time.
Despite significant recent advances in probabilistic meta-learning, it is common for practitioners to avoid using deep learning models due to a comparative lack of interpretability. Instead, many practitioners simply use non-meta-models such as Gaussian processes with interpretable priors, and conduct the tedious procedure of training their model from scratch for each task they encounter. While this is justifiable for tasks with a limited number of data points, the cubic computational cost of exact Gaussian process inference renders this prohibitive when each task has many observations. To remedy this, we introduce a family of models that meta-learn sparse Gaussian process inference. Not only does this enable rapid prediction on new tasks with sparse Gaussian processes, but since our models have clear interpretations as members of the neural process family, it also allows manual elicitation of priors in a neural process for the first time. In meta-learning regimes for which the number of observed tasks is small or for which expert domain knowledge is available, this offers a crucial advantage.