From inexact optimization to learning via gradient concentration
From MaRDI portal
From inexact optimization to learning via gradient concentration (scientific article)
Abstract: Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the error on future data (test error), for which the training data provides only partial information. In this view, the optimization problems that are practically feasible are based on inexact quantities that are stochastic in nature. In this paper, we show how probabilistic results, specifically gradient concentration, can be combined with results from inexact optimization to derive sharp test error guarantees. By considering unconstrained objectives we highlight the implicit regularization properties of optimization for learning.
This page was built for publication: From inexact optimization to learning via gradient concentration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6369924)
