Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent.
Krunoslav Lehman PavasovicAlain DurmusUmut SimsekliPublished in: CoRR (2023)
Keyphrases
- stochastic gradient descent
- heavy tails
- loss function
- least squares
- matrix factorization
- step size
- random forests
- support vector machine
- probability density function
- regularization parameter
- multiple kernel learning
- heavy tailed
- weight vector
- generative model
- image restoration
- machine learning
- image sequences
- image processing