Adaptive Gradient Descent without Descent

12. červenec 2020

Řečníci

O prezentaci

We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don't increase the stepsize too fast and 2) don't overstep the local curvature. No need for functional values, no line search, no information about the function except for the gradients. By following these rules, you get a method adaptive to the local geometry, with convergence guarantees depending only on smoothness in a neighborhood of a solution. Given that the problem is convex, our method will converge even if the global smoothness constant is infinity. As an illustration, it can minimize arbitrary continuously twice-differentiable convex function. We examine its performance on a range of convex and nonconvex problems, including logistic regression and matrix factorization.

Organizátor

Kategorie

O organizátorovi (ICML 2020)

The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

Uložení prezentace

Měla by být tato prezentace uložena po dobu 1000 let?

Jak ukládáme prezentace

Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %

Sdílení

Doporučená videa

Prezentace na podobné téma, kategorii nebo přednášejícího

Zajímají Vás podobná videa? Sledujte ICML 2020