研究人员开发了一种使用遗憾最小化进行校准的新框架，将先前针对特定损失函数的工作扩展到更广泛的一般损失函数。该方法利用 Bregman 散度来分析 $\alpha$-Tsallis 和 Lipschitz 损失等损失函数，实现了对维度依赖性有改进的对数遗憾。该研究还提出了 Be The Regularized Leader 算法的一种新颖遗憾等式，适用于一般损失函数。 AI
影响 为机器学习中的校准引入了通用的理论框架，有可能提高各种损失函数下模型的可靠性。
排序理由 该集群包含一篇详细介绍机器学习新理论框架和算法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.17269v1 Announce Type: cross Abstract: This work introduces a general framework for calibeating based on regret minimization. As compared to Foster and Hart's seminal calibeating work which had specialized treatments of Brier score (squared loss) and log loss, we consi…
This work introduces a general framework for calibeating based on regret minimization. As compared to Foster and Hart's seminal calibeating work which had specialized treatments of Brier score (squared loss) and log loss, we consider a large family of proper losses that includes …