Approximate Expected Utility Rationalization
We propose a new measure of deviations from expected utility theory. For any positive number~$e$, we give a characterization of the datasets with a rationalization that is within~$e$ (in beliefs, utility, or perceived prices) of expected utility theory. The number~$e$ can then be used as a measure of how far the data is to expected utility theory. We apply our methodology to data from three large-scale experiments. Many subjects in those experiments are consistent with utility maximization, but not with expected utility maximization. Our measure of distance to expected utility is correlated with subjects' demographic characteristics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales
Among the remarkable emergent capabilities of large language models (LMs) is free-text rationalization; beyond a certain scale, large LMs are capable of generating seemingly useful rationalizations, which in turn, can dr…
Does Self-Rationalization Improve Robustness to Spurious Correlations?
Rationalization is fundamental to human reasoning and learning. NLP models trained to produce rationales along with predictions, called self-rationalization models, have been investigated for their interpretability and u…
DecoderComputational Rationalization: The Inverse Equilibrium Problem
Modeling the purposeful behavior of imperfect agents from a small number of observations is a challenging task. When restricted to the single-agent decision-theoretic setting, inverse optimal control techniques assume th…
On The Equivalence Of The Mean Variance Criterion And Stochastic Dominance Criteria
We study the necessary and sufficient conditions under which the Mean-Variance Criterion (MVC) is equivalent to the Maximum Expected Utility Criterion (MEUC), for two lotteries. Based on Chamberlain (1983), we conclude t…
validFast Estimation for Privacy and Utility in Differentially Private Machine Learning
Recently, differential privacy has been widely studied in machine learning due to its formal privacy guarantees for data analysis. As one of the most important parameters of differential privacy, $\epsilon$ controls the …
BIG-bench Machine Learning