两篇新研究论文探讨了在高斯分布下学习半空间的计算硬度。第一篇论文关注齐次半空间，在学习错误（LWE）假设下证明了近乎最优的硬度结果，并将先前的工作扩展到这种情况。第二篇论文为学习半空间交集提供了改进的硬度结果，在统计查询框架下提供了无条件的界限，并缩小了学习多个半空间的上界和下界之间的差距。 AI
影响 这些理论发现可以通过确定学习能力的基本限制，为开发更有效和更安全的机器学习算法提供信息。
排序理由 两篇在arXiv上发表的学术论文，提出了关于机器学习中计算硬度的新理论结果。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.26446v1 Announce Type: new Abstract: We study three problems that involve identifying homogeneous halfspaces under Gaussian distributions: agnostic learning, one-sided reliable learning, and fairness auditing. In each of these problems, we are given labeled examples $(…
We study three problems that involve identifying homogeneous halfspaces under Gaussian distributions: agnostic learning, one-sided reliable learning, and fairness auditing. In each of these problems, we are given labeled examples $(\mathbf{x}, \mathrm{y})$ drawn from an unknown d…
arXiv:2402.15995v2 Announce Type: replace-cross Abstract: We show strong (and surprisingly simple) lower bounds for weakly learning intersections of halfspaces in the improper setting. Strikingly little is known about this problem. For instance, it is not even known if there is a…