研究人员为在线学习中的Follow-the-Perturbed-Leader (FTPL)算法开发了一种新的自适应学习率方法。该方法引入了代理概率函数，能够在无需精确计算概率的情况下实现依赖于概率的自适应。该方法将Best-of-Both-Worlds保证扩展到具有Pareto扰动和专家建议设置的FTPL，并保持了FTPL的计算效率。 AI
影响 为在线学习算法引入了一种新颖的自适应学习率方法论，有可能提高在多臂老虎机和专家建议问题中的性能。
排序理由 该集群包含一篇详细介绍新算法方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.06043v1 Announce Type: new Abstract: Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, adaptive learning rates defined in terms of the arm-s…
Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, adaptive learning rates defined in terms of the arm-selection probabilities, obtained by solving conv…