PAC Learning with Multiple Correct Answers
The main finding is that demonstrations can be much harder than full sets, and even than bandit feedback, both in which classes can be learned and in how many examples are needed.
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The main finding is that demonstrations can be much harder than full sets, and even than bandit feedback, both in which classes can be learned and in how many examples are needed.
We continue the study of relatively smart learning, introduced by Dughmi and Pour (2026), which asks a supervised learner to compete, marginal by marginal, with every distribution-fixed error guarantee soundly certifiable from unlabeled data. They showed that the One-Inclusion Graph (OIG) learner is relatively smart wi...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.