Convergence rate of stochastic gradient with constant step size
By Mark W. Schmidt. 2014
20 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Modeling and Simulation, Statistics and Probability, 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
- Fabian Pedregosa
- Peter Richtárik
- Rémi Leblond
- Aurélien Lucchi
- Thomas Hofmann
- Brian McWilliams
- Martin Jaggi
In Modeling and Simulation
In Statistics and Probability
- Fabian Pedregosa
- Aurélien Lucchi
- Simon Lacoste-Julien
- Thomas Hofmann
- Val Tannen
- Brian McWilliams
- Yinjun Wu
- Rémi Leblond
In Optimization & Training
- Simon Lacoste-Julien
- Fabian Pedregosa
- Peter Richtárik
- Rémi Leblond
- Aurélien Lucchi
- Thomas Hofmann
- Brian McWilliams
- Val Tannen
Citations in the corpus
- Improved asynchronous parallel optimization analysis for stochastic incremental methods (2018, methodology): “For reference, we start by giving the rate of convergence of serial Sgd (see e.g. Schmidt, 2014).”
- Variance Reduced Stochastic Gradient Descent with Neighbors (2015, background): “We also note that the geometric convergence of SGD with a constant step size to a neighborhood of the solution (also proven in [8]) can arise as a special case in our analysis.”
- PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models (2020, background): “vergence analysis for provenance-annotated iterations One concern in using GBM is whether the model parameters ultimately converge. This has been extensively studied in the machine learning community [3, 29, 36, 48, 49]. In [3], convergence conditions have been provided for GD and SGD over strong co”