For example, in personalized medical diagnostics, a model is built based on historical data to facilitate an optimal treatment for a new patient (Bica et al., 2021).

Traditional denoising diffusion models are defined on finite-dimension Euclidean spaces (Song and Ermon, 2019; Song et al., 2021; Ho et al., 2020; Dhariwal and Nichol, 2021).

While extensive research on uncertainty estimation has been conducted with unimodal data, uncertainty estimation for multimodal data remains a challenge. Neural processes (NPs) have been demonstrated to be an effective uncertainty estimation method for unimodal data by providing the reliability of Gaussian processes with efficient and powerful DNNs.

Conditioning on observations, itdirectly performs inference on the target stochastic process.

Neural processes (NPs) formulate exchangeable stochastic processes and are promising models for meta learning that do not require gradient updates during thetestingphase.

Statistical approaches [5] for the forecasting problem are fairly newcompared tomore traditional mechanistic approaches [13, 38].