The Sample Complexity of Multi-Distribution Learning for VC Classes

07/22/2023
by   Pranjal Awasthi, et al.
0

Multi-distribution learning is a natural generalization of PAC learning to settings with multiple data distributions. There remains a significant gap between the known upper and lower bounds for PAC-learnable classes. In particular, though we understand the sample complexity of learning a VC dimension d class on k distributions to be O(ϵ^-2ln(k)(d + k) + min{ϵ^-1 dk, ϵ^-4ln(k) d}), the best lower bound is Ω(ϵ^-2(d + k ln(k))). We discuss recent progress on this problem and some hurdles that are fundamental to the use of game dynamics in statistical learning.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset