Water from Two Rocks: Maximizing the Mutual Information
Water from Two Rocks: Maximizing the Mutual Information
复制标题
两块岩石中的水：最大化互信息
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
G. Schoenebeck
中科院分区：
文献类型：
--
作者：
Yuqing Kong;G. Schoenebeck
我们在学习问题、协同训练和无需验证的预测启发之间建立了自然的联系（与同行预测相关），并使用相同的信息论方法同时解决它们。在协同训练/多视图学习中，目标是将两个数据视图聚合成潜在标签的预测。我们展示了如何通过将问题简化为优化问题来最佳地组合两个数据视图。我们的工作为总体设置提供了统一且严格的方法。在无需验证的预测引发中，我们寻求设计一种机制，在该机制无法访问真实情况的情况下，从代理那里引发高质量的预测。通过假设代理的信息是对结果的独立调节，我们提出了在单任务和多任务设置中说真话都是严格平衡的机制。我们的多任务机制还具有这样的特性：说真话均衡比任何其他策略配置文件支付更好，并且严格优于任何其他“非排列”策略配置文件。
We build a natural connection between the learning problem, co-training, and forecast elicitation without verification (related to peer-prediction) and address them simultaneously using the same information theoretic approach. In co-training/multiview learning, the goal is to aggregate two views of data into a prediction for a latent label. We show how to optimally combine two views of data by reducing the problem to an optimization problem. Our work gives a unified and rigorous approach to the general setting. In forecast elicitation without verification we seek to design a mechanism that elicits high quality forecasts from agents in the setting where the mechanism does not have access to the ground truth. By assuming the agents' information is independent conditioning on the outcome, we propose mechanisms where truth-telling is a strict equilibrium for both the single-task and multi-task settings. Our multi-task mechanism additionally has the property that the truth-telling equilibrium pays better than any other strategy profile and strictly better than any other "non-permutation" strategy profile.
DOI：
--
发表时间：
2016-05
期刊：
Advances in neural information processing systems
影响因子：
--
作者：
Alexander J. Ratner;Christopher De Sa;Sen Wu;Daniel Selsam;C. Ré
通讯作者：
Alexander J. Ratner;Christopher De Sa;Sen Wu;Daniel Selsam;C. Ré