arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.02423cs.LGcs.MAstat.ML
收藏

合作推理理论的推广

Generalizing the theory of cooperative inference

Rutgers University—Newark(罗格斯大学纽瓦克分校)

Pei Wang, Pushpi Paranamana, Patrick Shafto

摘要:

协作信息共享是人类学习理论的重要组成部分,对机器学习也有潜在的意义。先前的工作得出的条件,实现最佳的合作推理强,相对限制性的假设。我们放松这些假设,证明收敛的任何离散联合分布,鲁棒性,通过等价类和扰动下的稳定性,和有效性,从原始联合分布的结构性质的界限。我们提供几何解释,连接和最佳运输的影响,连接到重要性采样,并概述了开放的问题和挑战,实现合作推理的承诺。

英文摘要:

Cooperation information sharing is important to theories of human learning and has potential implications for machine learning. Prior work derived conditions for achieving optimal Cooperative Inference given strong, relatively restrictive assumptions. We relax these assumptions by demonstrating convergence for any discrete joint distribution, robustness through equivalence classes and stability under perturbation, and effectiveness by deriving bounds from structural properties of the original joint distribution. We provide geometric interpretations, connections to and implications for optimal transport, and connections to importance sampling, and conclude by outlining open questions and challenges to realizing the promise of Cooperative Inference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑