论文标题
山姆作为贝叶斯的最佳放松
SAM as an Optimal Relaxation of Bayes
论文作者
论文摘要
清晰度感知的最小化（SAM）和相关的对抗性深度学习方法可以大大改善概括，但是它们的潜在机制尚未完全了解。在这里，我们将SAM建立为贝叶斯物镜的放松，其中通过使用所谓的Fenchel Biconjugate获得了最佳凸下限的预期负损失。该连接使SAM的新的类似Adam的扩展可以自动获得合理的不确定性估计，同时有时也提高了其准确性。通过连接对抗和贝叶斯方法，我们的工作为鲁棒性开辟了一条新的途径。
Sharpness-aware minimization (SAM) and related adversarial deep-learning methods can drastically improve generalization, but their underlying mechanisms are not yet fully understood. Here, we establish SAM as a relaxation of the Bayes objective where the expected negative-loss is replaced by the optimal convex lower bound, obtained by using the so-called Fenchel biconjugate. The connection enables a new Adam-like extension of SAM to automatically obtain reasonable uncertainty estimates, while sometimes also improving its accuracy. By connecting adversarial and Bayesian methods, our work opens a new path to robustness.
