Work

Tightening the Sample Complexity of Empirical Risk Minimization via Preconditioned Stability.

Year: 2016

Type: preprint

Abstract: We tighten the sample complexity of empirical risk minimization (ERM) associated with a class of generalized linear models that include linear and logistic regression. In particular, we conclude that ERM attains the optimal sample complexity for linear regression. Our analysis relies on a new notion of stability, called preconditioned stability, which may be of independent interest.

Source: arXiv (Cornell University)

Authors: Alon Gonen, Shai Shalev‐Shwartz

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2295676596

Cites: 22

Cited by: 5

Related to: 10