Skip to yearly menu bar Skip to main content


Poster

Algorithmic Stability and Hypothesis Complexity

Tongliang Liu · Gábor Lugosi · Gergely Neu · Dacheng Tao

Gallery #97

Abstract:

We introduce a notion of algorithmic stability of learning algorithms---that we term \emph{hypothesis stability}---that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of any learning algorithm in terms of its hypothesis stability. The bounds are based on martingale inequalities in the Banach space to which the hypotheses belong. We apply the general bounds to bound the performance of some learning algorithms based on empirical risk minimization and stochastic gradient descent.

Live content is unavailable. Log in and register to view live content