Poster
in
Workshop: Deep Generative Model in Machine Learning: Theory, Principle and Efficacy
Flow Matching Neural Processes
Hussen Abu Hamad · Dan Rosenbaum
Keywords: [ neural processes ] [ flow matching ] [ generative models ] [ stochastic processes ] [ probabilistic modeling ]
Neural processes (NPs) are a class of models that learn stochastic processes directly from data and can be used for inference, sampling, and conditional sampling.We introduce a new NP model, which is based on flow matching, a generative modeling paradigm that has demonstrated strong performance on various data modalities. Our model is simple to implement, is efficient in training and evaluation, and outperforms previous state-of-the-art methods on various benchmarks including synthetic 1D Gaussian processes data, 2D images, and real-world weather data.