Noise and Fluctuation of Finite Learning Rate Stochastic Gradient Descent
December 07, 2020 Β· Declared Dead Β· π International Conference on Machine Learning
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Kangqiao Liu, Liu Ziyin, Masahito Ueda
arXiv ID
2012.03636
Category
stat.ML: Machine Learning (Stat)
Cross-listed
cs.LG
Citations
45
Venue
International Conference on Machine Learning
Last Checked
2 months ago
Abstract
In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus is on deriving exactly solvable results and discussing their implications. The main contributions of this work are to derive the stationary distribution for discrete-time SGD in a quadratic loss function with and without momentum; in particular, one implication of our result is that the fluctuation caused by discrete-time dynamics takes a distorted shape and is dramatically larger than a continuous-time theory could predict. Examples of applications of the proposed theory considered in this work include the approximation error of variants of SGD, the effect of minibatch noise, the optimal Bayesian inference, the escape rate from a sharp minimum, and the stationary covariance of a few second-order methods including damped Newton's method, natural gradient descent, and Adam.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Machine Learning (Stat)
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Distilling the Knowledge in a Neural Network
R.I.P.
π»
Ghosted
Layer Normalization
R.I.P.
π»
Ghosted
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
R.I.P.
π»
Ghosted
Domain-Adversarial Training of Neural Networks
R.I.P.
π»
Ghosted
Deep Learning with Differential Privacy
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted