Journées de l'optimisation 2019

HEC Montréal, 13-15 mai 2019

JOPT2019

HEC Montréal, 13 — 15 mai 2019

Horaire Auteurs Mon horaire

MD1 Tutorial - Modern Optimization for Structured Machine Learning

13 mai 2019 15h30 – 17h10

Salle: CPA du Québec

Présidée par Jean-Yves Potvin

1 présentation

  • 15h30 - 17h10

    Modern Optimization for Structured Machine Learning

    • Simon Lacoste-Julien, prés., Université de Montréal

    Machine learning has become a popular application domain for modern optimization techniques, pushing its algorithmic frontier. The need for large scale optimization algorithms which can handle millions of dimensions or data points, typical for the big data era, have brought a resurgence of interest for first order algorithms, making us revisit the venerable stochastic gradient method [Robbins-Monro 1951]as well as the Frank-Wolfe algorithm [Frank-Wolfe 1956]. In this talk, I will review recent improvements on these algorithms which can exploit the structure of modern machine learning approaches. I will explain why the Frank-Wolfe algorithm has become so popular lately; and present a surprising tweak on the stochastic gradient method which yields a fast linear convergence rate. Motivating applications will include weakly supervised video analysis and structured prediction problems.

Retour