Large-Scale Machine Learning with Stochastic Gradient Descent
Léon Bottou · Physica-Verlag eBooks · 2010
During the last decade, the data sizes have grown faster than the speed of processors. In this context, the capabilities of statistical machine learning methods is limited by the computing time rather than the sample size. A more precise analysis uncovers qualitatively different tradeoffs for the case of small-scale and large-scale learning problems. The large-scale case involves the computational complexity of the underlying optimization algorithm in non-trivial ways. Unlikely optimization algorithms such as stochastic gradient descent show amazing performance for large-scale problems. In particular, second order stochastic gradient and averaged stochastic gradient are asymptotically efficient after a single pass on the training set.
Cited by 5,540 works. doi:10.1007/978-3-7908-2604-3_16
Authors
References
- Learning Internal Representations by Error Propagation
- Support-Vector Networks
- Regression Shrinkage and Selection Via the Lasso
- Some methods for classification and analysis of multivariate observations
- Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
- ADAPTIVE SWITCHING CIRCUITS
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Numerical Methods for Unconstrained Optimization and Nonlinear Equations
- Acceleration of Stochastic Approximation by Averaging
- Advances in Neural Information Processing Systems 19