@inproceedings{venkataramanan2025distance,
    type = {inproceedings},
    key = {venkataramanan2025distance},
    author = {Aishwarya Venkataramanan and Joachim Denzler},
    title = {Distance-informed Neural Processes},
    booktitle = {Annual Conference on Neural Information Processing Systems (NeurIPS)},
    year = {2025},
    abstract = {We propose the Distance-informed Neural Process (DNP), a novel variant of Neural Processes that improves uncertainty estimation by combining global and distance-aware local latent structures. Standard Neural Processes (NPs) often rely on a global latent variable and struggle with uncertainty calibration and capturing local data dependencies. DNP addresses these limitations by introducing a global latent variable to model task-level variations and a local latent variable to capture input similarity within a distance-preserving latent space. This is achieved through bi-Lipschitz regularization, which bounds distortions in input relationships and encourages the preservation of relative distances in the latent space. This modeling approach allows DNP to produce better-calibrated uncertainty estimates and more effectively distinguish in- from out-of-distribution data. Empirical results demonstrate that DNP achieves strong predictive performance and improved uncertainty calibration across regression and classification tasks.},
    groups = {uncertainty},
    publisher = {},
    volume = {},
    pages = {},
    doi = {10.48550/arXiv.2508.18903},
    url = {},
    arxiv = {https://arxiv.org/abs/2508.18903},
    code = {},
    note = {(accepted at NeurIPS)},
}