Bootstrapping Neural Processes

2020/08/07 by Lee, Juho, Lee, Yoonho, Kim, Jungtaek +3 · 5 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2008.02956

Abstract

Unlike in the traditional statistical modeling for which a user typically hand-specify a prior, Neural Processes (NPs) implicitly define a broad class of stochastic processes with neural networks. Given a data stream, NP learns a stochastic process that best describes the data. While this "data-driven" way of learning stochastic processes has proven to handle various types of data, NPs still rely on an assumption that uncertainty in stochastic processes is modeled by a single latent variable, which potentially limits the flexibility. To this end, we propose the Boostrapping Neural Process (BNP), a novel extension of the NP family using the bootstrap. The bootstrap is a classical data-driven technique for estimating uncertainty, which allows BNP to learn the stochasticity in NPs without assuming a particular form. We demonstrate the efficacy of BNP on various types of data and its robustness in the presence of model-data mismatch.

Cited by

• Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
• Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructions
• Amortising Inference and Meta-Learning Priors in Neural Networks
• GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
• Distance-informed Neural Processes
• Uncertainty-aware Accurate Elevation Modeling for Off-road Navigation via Neural Processes

Related

• Martingale Posterior Neural Processes
• The Neural Process Family: Survey, Applications and Perspectives
• Neural Processes
• Neural Bootstrapper
• Diffusion-Augmented Neural Processes