Seminar | September 16 | 11 a.m.-12 p.m. | Sutardja Dai Hall, 310 (Banatao Auditorium)
Abstract: Whether a model's performance on a given domain can be extrapolated to other settings depends on whether it has learned generalizable structure. We formulate this as the problem of theory transfer, and provide a tractable way to measure a theory's transferability. We derive confidence intervals for transferability that ensure coverage in finite samples, and apply our approach to evaluate the transferability of predictions of certainty equivalents across different subject pools. We find that models motivated by economic theory perform more reliably than black-box machine learning methods at this transfer prediction task.
All Audiences, Faculty, Students - Graduate
All Audiences
naomiy@berkeley.edu, 510-710-8488
Naomi Yamasaki, naomiy@berkeley.edu, 510-710-8488