Optimal Cooperative Inference
Optimal Cooperative Inference
复制标题
DOI：
--
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
Scott Cheng-Hsin Yang;Yue Yu;A. Givchi;Pei Wang;Wai Keen Vong;Patrick Shafto
中科院分区：
文献类型：
--
作者：
Scott Cheng-Hsin Yang;Yue Yu;A. Givchi;Pei Wang;Wai Keen Vong;Patrick Shafto
数据的合作传输通过有效地将学习者之间的经验结合在一起，促进了知识的快速积累。虽然在人类学习中有很好的研究，并且越来越多地在机器学习中，但我们缺乏正式的框架来推理合作推理的好处和局限性。我们提出了这样一个框架。我们引入了新的指标来衡量概率和协作信息传输的有效性。在确定性环境下，我们将我们的指数与众所周知的教学维度联系起来。我们证明了实现最优合作推理的条件，其中包括一个表示定理，该定理限制了为合作推理优化的学习者的归纳偏差形式。我们最后展示了这些原则如何为机器学习算法的设计提供信息，并讨论了对人类和机器学习的影响。
Cooperative transmission of data fosters rapid accumulation of knowledge by efficiently combining experiences across learners. Although well studied in human learning and increasingly in machine learning, we lack formal frameworks through which we may reason about the benefits and limitations of cooperative inference. We present such a framework. We introduce novel indices for measuring the effectiveness of probabilistic and cooperative information transmission. We relate our indices to the well-known Teaching Dimension in deterministic settings. We prove conditions under which optimal cooperative inference can be achieved, including a representation theorem that constrains the form of inductive biases for learners optimized for cooperative inference. We conclude by demonstrating how these principles may inform the design of machine learning algorithms and discuss implications for human and machine learning.