Spectral Convolutional Conditional Neural Processes

arXiv:2404.13182v1 Announce Type: new
Abstract: Conditional Neural Processes (CNPs) constitute a family of probabilistic models that harness the flexibility of neural networks to parameterize stochastic processes. Their capability to furnish well-calibrated predictions, combined with simple maximum-likelihood training, has established them as appealing solutions for addressing various learning problems, with a particular emphasis on meta-learning. A prominent member of this family, Convolutional Conditional Neural Processes (ConvCNPs), utilizes convolution to explicitly introduce translation equivariance as an inductive bias. However, ConvCNP's reliance on …

abstract arxiv capability cs.lg family flexibility harness likelihood maximum maximum-likelihood meta meta-learning networks neural networks predictions processes simple solutions stochastic them training type