LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
Arthur Chiron, Franck Mamalet, Thomas Massena, Thomas Deltort, Mathieu Serrurier
IRIT, EPE UT · IRIT, DTIPG - SNCF, UT3 · IRIT, DTIPG - SNCF, UT3 · IRIT · IRIT, UT2J
cs.LG, stat.ML
Submitted: 2026-07-08
Code: https://github.com/deel-ai/deel-torchlip
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Explaining and Harnessing Adversarial Examples
- Robust Models are less Over-Confident
- The Limitations of Model Uncertainty in Adversarial Settings
- On the Robustness of Adversarial Training Against Uncertainty Attacks
- Intriguing properties of neural networks
- Calibration of Neural Networks
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks