The Rashomon effect is a mixed blessing in responsible machine learning.

A central notion in practical and theoretical machine learning is that of a weak learner, classifiers that achieve better-than-random performance (on any given distribution over data), even by a small margin. Such weak learners form the practical basis for canonical machine learning methods such as boosting.

's are real-valued weights depending on the accuracy of h

Data valuation has emerged as a powerful framework for quantifying each datum's

Neural Information Processing Systems http://nips.cc/

Since weak learners perform only marginallybetter than random guesses, such subroutines constitute aweakerassumption than the availability of an accurate supervised learning oracle. Weprovethat the sample complexity and running time bounds of the proposed method do not explicitly dependonthenumberofstates. While existing results on boosting operate on convex losses, the value function over policies is non-convex.