Bootstrapping neural processes

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 relies 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 Bootstrapping 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.

Authors

• Juho Lee Kim Jaechul Graduate School of AI, KAIST, Seoul, South Korea
• Yoonho Lee
• Jungtaek Kim
• Eunho Yang Korea Advanced Institute of Science & Technology (KAIST) AITRICS
• Sung Ju Hwang
• Yee Whye Teh

Keywords

No keywords are indexed for this paper.