paper-with-me

Papers

GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data

2021-06-09 · Jens Petersen, Gregor Köhler, David Zimmerer, Fabian Isensee, Paul F. Jäger, Klaus H. Maier-Hein

Neural Processes (NPs) are a family of conditional generative models that are able to model a distribution over functions, in a way that allows them to perform predictions at test time conditioned on a number of context points. A recent addition to this family, Convolutional Conditional Neural Processes (ConvCNP), have shown remarkable improvement in performance over prior art, but we find that they sometimes struggle to generalize when applied to time series data. In particular, they are not robust to distribution shifts and fail to extrapolate observed patterns into the future. By incorporating a Gaussian Process into the model, we are able to remedy this and at the same time improve performance within distribution. As an added benefit, the Gaussian Process reintroduces the possibility to sample from the model, a key feature of other members in the NP family.

📄 PDF Abstract BibTeX arXiv:2106.04967

Code (1)

MIC-DKFZ/gpconvcnp 공식 구현 pytorch

Tasks

Time SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Spectral Convolutional Conditional Neural Processes

2024-04-19 · Peiman Mohseni, Nick Duffield

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 prediction…

Inductive BiasMeta-Learning

Convolutional Conditional Neural Processes

2019-10-29 · ICLR 2020 1 · Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong, James Requeima 외

We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for…

Inductive BiasTime SeriesTime Series AnalysisTranslation+1

Convolutional conditional neural processes for local climate downscaling

2021-01-20 · Anna Vaughan, Will Tebbutt, J. Scott Hosking, Richard E. Turner

A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently developed class of models that allow de…

Gaussian Processes

Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs

2025-11-27 · Feyza Eksen, Stefan Oehmcke, Stefan Lüdtke arxiv

Accurate sensor placement is critical for modeling spatio-temporal systems such as environmental and climate processes. Neural Processes (NPs), particularly Convolutional Conditional Neural Processes (ConvCNPs), provide …

Sim2Real for Environmental Neural Processes

2023-10-30 · Jonas Scholz, Tom R. Andersson, Anna Vaughan, James Requeima 외

Machine learning (ML)-based weather models have recently undergone rapid improvements. These models are typically trained on gridded reanalysis data from numerical data assimilation systems. However, reanalysis data come…