On the learnability of discrete distributions

Authors: Michael J. Kearns, Yishay Mansour, Dana Ron, Ronitt Rubinfeld, Robert E. Schapire, Linda Sellie - ACM Symposium on Theory of Computing, STOC 1994 cited by 287

We introduce and investigate a new model of learning probability distributions from independent draws. Our model is inspired by the popular Probably Approximately Correct (PAC) model for learning boolean functions from labeled