In plain words: Course notes explain the math behind training machine learning systems, showing how to adjust them so they learn efficiently. Compiled from a Princeton course and tutorial sessions, they lay out the core tools for making training faster and more reliable.

Abstract

Lecture notes on optimization for machine learning, derived from a course at Princeton University and tutorials given in MLSS, Buenos Aires, as well as Simons Foundation, Berkeley.

Elad Hazan
arXiv:1909.03550 · cs.LG, stat.ML · submitted Sep 8, 2019
abstract · pdf · html