Convergence Rate Analysis of a Stochastic Trust-Region Method via Supermartingales
By Jose H. Blanchet, Coralia Cartis, Matt Menickelly, Katya Scheinberg. 2019
143 citations recorded by the source corpus.
We propose a novel framework for analyzing convergence rates of stochastic optimization algorithms with adaptive step sizes. This framework is based on analyzing properties of an underlying generic...
Subfields: Artificial Intelligence, Computational Mechanics, Optimization & Training
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Simon Lacoste-Julien
- Gauthier Gidel
- Issam Hadj Laradji
- Peter Richtárik
- Sharan Vaswani
- Nicolas Loizou
- Mark W. Schmidt
- Aaron Mishkin
In Computational Mechanics
- Simon Lacoste-Julien
- Gauthier Gidel
- Sharan Vaswani
- Issam Hadj Laradji
- Peter Richtárik
- Mark W. Schmidt
- Aaron Mishkin
- Nicolas Loizou
In Optimization & Training
- Simon Lacoste-Julien
- Issam Hadj Laradji
- Gauthier Gidel
- Sharan Vaswani
- Nicolas Loizou
- Peter Richtárik
- Mark W. Schmidt
- Aaron Mishkin
Citations in the corpus
- Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates (2019, background): “Other work [11, 26] exploring trust-region methods assume that the model is sufficiently accurate, which is not guaranteed in the general stochastic setting.”