Pith. sign in

REVIEW 5 cited by

Convolutional Conditional Neural Processes

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1910.13556 v5 pith:2JHNZTVM submitted 2019-10-29 stat.ML cs.LG

Jonathan Gordon , Wessel P. Bruinsma , Andrew Y. K. Foong , James Requeima , Yann Dubois , Richard E. Turner This is my paper · ORCID
classification stat.MLcs.LG
keywords neuralconvolutionaldataequivariancetranslationconditionaldemonstrateprocess
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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 many learning problems including time series modelling, spatial data, and images. The model embeds data sets into an infinite-dimensional function space as opposed to a finite-dimensional vector space. To formalize this notion, we extend the theory of neural representations of sets to include functional representations, and demonstrate that any translation-equivariant embedding can be represented using a convolutional deep set. We evaluate ConvCNPs in several settings, demonstrating that they achieve state-of-the-art performance compared to existing NPs. We demonstrate that building in translation equivariance enables zero-shot generalization to challenging, out-of-domain tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Amortized In-Context Bayesian Posterior Estimation

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A benchmark of in-context Bayesian posterior estimators shows the reverse-KL objective with transformers and normalizing flows outperforms forward-KL neural posterior estimation on predictive and out-of-distribution tasks.

  2. Geometric Neural Process Fields

    cs.CV 2025-02 conditional novelty 6.0 of 10

    Geometric Neural Process Fields use Gaussian geometric bases and hierarchical latent variables to improve neural process generalization to 1D, 2D, and 3D signals.

  3. Distance-informed Neural Processes

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A neural process with a bi-Lipschitz-regularized local encoder achieves better uncertainty calibration and OOD detection than existing NP variants.

  4. Uncertainty-aware Accurate Elevation Modeling for Off-road Navigation via Neural Processes

    cs.RO 2025-08 conditional novelty 5.0 of 10

    A semantic-conditioned neural process with local ball-query attention estimates off-road terrain elevation and uncertainty more accurately than prior baselines.

  5. Exploring Convolutional Neural Processes for Weather Downscaling

    cs.LG 2026-07 conditional novelty 4.0 of 10

    ConvCNPs with a high-resolution elevation MLP downscale Swiss Tmax to 1.31°C MAE and CRPS skill 0.524 vs bilinear ERA5-Land, but stay overconfident and fail zero-shot on off-grid stations.

Pith tools