{"slug": "list-lipschitz-scaling-training-for-robust-and-calibrated-neural-networks", "title": "LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks", "summary": "Researchers introduced Lipschitz Scaling Training (LiST), a method that adjusts the Lipschitz constant of neural networks to achieve out-of-the-box calibration while balancing accuracy and robustness. LiST outperforms baselines on CIFAR-10/100 and Tiny-ImageNet, producing calibrated models without post-hoc tuning.", "body_md": "arXiv:2607.07745v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/list-lipschitz-scaling-training-for-robust-and-calibrated-neural-networks", "canonical_source": "https://arxiv.org/abs/2607.07745", "published_at": "2026-07-10 04:00:00+00:00", "updated_at": "2026-07-10 04:16:38.747241+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-safety", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/list-lipschitz-scaling-training-for-robust-and-calibrated-neural-networks", "markdown": "https://wpnews.pro/news/list-lipschitz-scaling-training-for-robust-and-calibrated-neural-networks.md", "text": "https://wpnews.pro/news/list-lipschitz-scaling-training-for-robust-and-calibrated-neural-networks.txt", "jsonld": "https://wpnews.pro/news/list-lipschitz-scaling-training-for-robust-and-calibrated-neural-networks.jsonld"}}