{"ID":6267446,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-11T08:29:44.454854982Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07745","arxiv_id":"2607.07745","title":"LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks","abstract":"While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge. Lipschitz-constrained models guarantee robustness by design, yet the manual selection of the Lipschitz constraint L governs the resulting accuracy-robustness trade-off, and their calibration properties remain largely underexplored. In this work, we highlight a theoretical and empirical link between the enforced Lipschitz constraint and Temperature Scaling, a state-of-the-art calibration method. Specifically, we find that for a given training scheme, there exists a non-trivial value L* that yields an out-of-the-box calibrated network, and that calibration acts as a principled criterion to select a well-defined operating point on the accuracy-robustness Pareto front. Leveraging these insights, we introduce Lipschitz Scaling Training (LiST), a novel training paradigm that iteratively adjusts the global Lipschitz constant to reach this operating point. Through a margin parameter in the training loss, LiST further enables the construction of a fully calibrated Pareto front, allowing users to navigate the accuracy-robustness trade-off while remaining calibrated throughout. At convergence, LiST also enables the reintegration of calibration data into training, improving sample efficiency without sacrificing calibration. We validate LiST on CIFAR-10/100 and Tiny-ImageNet, demonstrating competitive accuracy and robustness against constrained and unconstrained baselines, while remaining calibrated out of the box. Code is available at GitHub.","short_abstract":"While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge. Lipschitz-constrained models guarantee robustness by design, yet the manual selection of the Lipschitz const...","url_abs":"https://arxiv.org/abs/2607.07745","url_pdf":"https://arxiv.org/pdf/2607.07745v1","authors":"[\"Arthur Chiron\",\"Franck Mamalet\",\"Thomas Massena\",\"Thomas Deltort\",\"Mathieu Serrurier\"]","published":"2026-07-08T08:34:01Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"stat.ML\"]","methods":"[]","has_code":false}