Can we redesign surveys to elicit true preferences? If we could, corporations, policymakers, and academics who rely on surveys would make better-informed conclusions. We have a clever idea, Quadratically Constrained Surveys, that can help with online surveys.
How can we learn-to-recommend few-shot items with sparse interactions? This work presents a new perspective on the classic long-tail challenge faced by collaborative filtering models by formulating a meta-learning framework for few-shot recommendation.
Should one teach open-ended courses such as Jazz Improvisation the same way as teaching non-open-ended courses such as Intro to Computer Science? This work presents an exploratory study on the challenges and concerns of faculty and students in the arts, humanities, and social sciences about education at scale.
