让高斯过程具备元学习能力，加速新任务推理并支持人工设定先验。
Sparse Gaussian Neural Processes
- 用神经过程框架实现稀疏高斯过程的元学习
- 在少样本任务上实现快速预测，克服传统方法计算量大问题
- 首次支持在神经过程中手动设定可解释先验，适合有领域知识的研究者
尽管概率元学习近年取得显著进展，由于深度模型可解释性差，许多实践者仍偏好使用具有可解释先验的非元学习模型（如高斯过程），需为每个任务从头训练，效率低下。当任务数据量较大时，精确高斯过程推断的立方级计算成本使其难以应用。为此，我们提出一类元学习稀疏高斯过程推断的模型。该方法不仅实现了新任务上的快速预测，还因模型属于神经过程家族，首次支持在神经过程中手动提取先验。在任务数量有限或存在专家领域知识的元学习场景中，这一特性具有重要优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。