Eric Neyman's thesis delves into Algorithmic Bayesian Epistemology, applying computational and informational constraints to explore belief formation. The work highlights the importance of forming accurate beliefs despite limitations in information and computation.
The thesis covers a range of topics including forecast aggregation, online learning from expert advice, estimation theory, prediction markets, information design, and robust mechanism design. It addresses challenges such as incentivizing truthful information sharing and reasoning about uncertainty under various constraints.
Neyman's research contributes to understanding how individuals form beliefs in real-world scenarios where complete assimilation of all existing information is not feasible. By applying the algorithmic lens to Bayesian epistemology, he sheds light on fundamental questions in decision-making under uncertainty.
他の言語に翻訳
原文コンテンツから
arxiv.org
深掘り質問