English

Packed-Ensembles for Efficient Uncertainty Estimation

Machine Learning 2025-09-24 v4 Machine Learning

Abstract

Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection. However, hardware limitations of real-world systems constrain to smaller ensembles and lower-capacity networks, significantly deteriorating their performance and properties. We introduce Packed-Ensembles (PE), a strategy to design and train lightweight structured ensembles by carefully modulating the dimension of their encoding space. We leverage grouped convolutions to parallelize the ensemble into a single shared backbone and forward pass to improve training and inference speeds. PE is designed to operate within the memory limits of a standard neural network. Our extensive research indicates that PE accurately preserves the properties of DE, such as diversity, and performs equally well in terms of accuracy, calibration, out-of-distribution detection, and robustness to distribution shift. We make our code available at https://github.com/ENSTA-U2IS/torch-uncertainty.

Keywords

Cite

@article{arxiv.2210.09184,
  title  = {Packed-Ensembles for Efficient Uncertainty Estimation},
  author = {Olivier Laurent and Adrien Lafage and Enzo Tartaglione and Geoffrey Daniel and Jean-Marc Martinez and Andrei Bursuc and Gianni Franchi},
  journal= {arXiv preprint arXiv:2210.09184},
  year   = {2025}
}

Comments

Published as a conference paper at ICLR 2023 (notable 25%)

R2 v1 2026-06-28T03:49:55.855Z