两篇新的arXiv论文探讨了机器学习损失函数的理论方面。一篇论文调查了基于比例的损失函数，考察了它们的连续性和凸性等性质，以支持未来的研究。另一篇论文表征了在具有一般度量损失的学习中实现强通用贝叶斯一致性的条件，解决了该领域的一个开放性问题。 AI
影响 这些关于损失函数和贝叶斯一致性的理论进展有望在未来带来更强大、更高效的机器学习算法。
排序理由 两篇发表在arXiv上的学术论文，讨论了机器学习损失函数的理论方面。
AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →
arXiv:2605.05446v1 Announce Type: cross Abstract: Nonconvex methods have emerged as a dominant approach for low-rank matrix estimation, a problem that arises widely in machine learning and AI for learning and representing high-dimensional data. Existing analyses for these methods…
arXiv:2605.05808v1 Announce Type: cross Abstract: Algorithms in machine learning and AI do critically depend on at least three key components: (i) the risk function, which is the expectation of the loss function, (ii) the function space, which is often called the hypothesis space…
arXiv:2605.03823v1 Announce Type: new Abstract: We study strong universal Bayes-consistency in the realizable setting for learning with general metric losses, extending classical characterizations beyond $0$-$1$ classification \citep{bousquet_theory_2021, hanneke2021universalbaye…
We study strong universal Bayes-consistency in the realizable setting for learning with general metric losses, extending classical characterizations beyond $0$-$1$ classification \citep{bousquet_theory_2021, hanneke2021universalbayesconsistencymetric} and real-valued regression \…
arXiv:2411.04696v5 Announce Type: replace Abstract: Learning correlations from data forms the foundation of today's machine learning (ML) and artificial intelligence research. While contemporary methods enable the automatic discovery of complex patterns, they are prone to failure…
Algorithms in machine learning and AI do critically depend on at least three key components: (i) the risk function, which is the expectation of the loss function, (ii) the function space, which is often called the hypothesis space, and (iii) the set of probability measures, which…
Nonconvex methods have emerged as a dominant approach for low-rank matrix estimation, a problem that arises widely in machine learning and AI for learning and representing high-dimensional data. Existing analyses for these methods often require additional regularization to mitiga…