Dominating Distributions and Learnability

We consider PAC-learning where the distribution is known to the student. The problem addressed here is characterizing when learnability with respect to distribution D1 implies learnability with respect to distribution Dz. The answer to the above question depends on the learnability model. If the number of examples need not be bounded by a polynomial, it is sufficient to require that all sets which have zero probability with respect to Dz have zero

• Type: Conference
• Year: 1992
• Where: COLT
• Authors: Gyora M. Benedek, Alon Itai
• Keywords: COLT 1992, Distribution Dz, Learnability, Learnability Model, Machine Learning