We test the population rule learning model for symmetric normal-form games, and strongly reject: (i) no rule learning …

applied to state filtering and sequential parameter learning. This paper introduces robust state space models whose error …

Predictive power has always been the main research focus of learning algorithms with the goal of minimizing the test … on sparse learning in order to avoid overfitting which can greatly affect the accuracy of out-of-sample prediction … response whereas even sparse-learning methods can still preserve a high number of attributes in high-dimensional settings and …

statistical structure in this scientific learning problem, techniques of model selection and meta-analysis are not directly useful …. Combining Bayesian and frequentist approaches, I derive simple, intuitive rules for updating beliefs. The theory incorporates … accuracy and general applicability. I establish necessary and sufficient conditions for the consistency of the learning …

This paper uses deep learning to value derivatives. The approach is broadly applicable, and we use a call option on a … basket of stocks as an example. We show that the deep learning model is accurate and very fast, capable of producing …

trade, but their effectiveness crucially depends on the speed of learning. …

collective learning. The present paper provides a summary of this research. …

. They may fail to do so in similar but more demanding settings. Given the opportunity, they transfer learning from the …

accuracy is conducive to unstable best-response dynamics. We define the barrier to learning as the minimum level of noise which … the role of strategy restrictions in reducing or amplifying barriers to learning …

We study learning by privately informed forward-looking agents in a simple repeated-action setting of social learning …