Toward a grand unified theory of accelerations in optimization and machine learning

You are here: University of Vienna PHAIDRA Detail o:2070050

Open in new window

Title (deu)

Speaker / Lecturer

Ernest Ryu

Seoul National U

Description (deu)

Momentum-based acceleration of first-order optimization methods, first introduced by Nesterov, has been foundational to the theory and practice of large-scale optimization and machine learning. However, finding a fundamental understanding of such acceleration remains a long-standing open problem. In the past few years, several new acceleration mechanisms, distinct from Nesterov’s, have been discovered, and the similarities and dissimilarities among these new acceleration phenomena hint at a promising avenue of attack for the open problem. In this talk, we discuss the envisioned goal of developing a mathematical theory unifying the collection of acceleration mechanisms and the challenges that are to be overcome.

Keywords (deu)

One World Optimization Seminar

Subject (eng)

ÖFOS 2012 -- 101 -- Mathematics

Type (eng)

lecture

Language

[eng]

Persistent identifier

https://phaidra.univie.ac.at/o:2070050

Date created

2024-06-07