Skip to content

Publications

Preprints

Joint learning of RKHS and kernel sum-of-squares functions: a representer theorem and its convex dual

Louis Allain and Sébastien Da Veiga

Submitted to Computo, 2026

@misc{allain2026joint,
  title        = {Joint learning of {RKHS} and kernel sum-of-squares functions: a representer theorem and its convex dual},
  author       = {Allain, Louis and Da Veiga, S{\'e}bastien},
  year         = {2026},
  month        = aug,
  howpublished = {Submitted to Computo},
  url          = {https://lui5ito.github.io/ksos-computo-submission/}
}

Conference & Journal Papers

Asymmetric conformal prediction with penalized kernel sum-of-squares

Louis Allain, Sébastien Da Veiga, and Brian Staber

ICML 2026

@inproceedings{allain2026asymmetric,
  title     = {Asymmetric conformal prediction with penalized kernel sum-of-squares},
  author    = {Allain, Louis and Da Veiga, S{\'e}bastien and Staber, Brian},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  pages     = {1995--2052},
  year      = {2026},
  editor    = {Zhang, Tong and Dud{\'\i}k, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto},
  volume    = {306},
  series    = {Proceedings of Machine Learning Research},
  month     = jul,
  publisher = {PMLR},
  url       = {https://proceedings.mlr.press/v306/allain26a.html}
}

Scalable and adaptive prediction bands with kernel sum-of-squares

Louis Allain, Sébastien Da Veiga, and Brian Staber

NeurIPS 2025

@inproceedings{allain2025scalable,
  title     = {Scalable and adaptive prediction bands with kernel sum-of-squares},
  author    = {Allain, Louis and Da Veiga, S{\'e}bastien and Staber, Brian},
  booktitle = {Advances in Neural Information Processing Systems},
  pages     = {132590--132609},
  year      = {2025},
  editor    = {Belgrave, D. and Zhang, C. and Lin, H. and Pascanu, R. and Koniusz, P. and Ghassemi, M. and Chen, N.},
  volume    = {38},
  publisher = {Curran Associates, Inc.},
  doi       = {10.52202/085713-4417},
  url       = {https://papers.nips.cc/paper_files/paper/2025/hash/bff09ce4b210b185a265c9bcd58048bb-Abstract-Conference.html}
}

Theses & Technical Reports

Kernel methods for uncertainty quantification in machine learning predictions

Louis Allain · Supervised by Sébastien Da Veiga, Brian Staber, Clément Bénard

Master's thesis, ENSAI & Safran Tech, 2024

@mastersthesis{allain2024kernel,
  title  = {Kernel methods for uncertainty quantification in machine learning predictions},
  author = {Allain, Louis},
  school = {ENSAI \& Safran Tech},
  year   = {2024}
}

Earlier work: student projects and reports →