We study the generalization properties of stochastic gradient methods for learning with convex loss functions and linearly parameterized functions. We show that, in the absence of penalizations or constraints, the stability and approximation properties of the algorithm can be controlled by tuning either the step-size or the number of passes over the data. In this view, these parameters can be seen to control a form of implicit regularization. Numerical results complement the theoretical findings.
Generalization properties and implicit regularization for multiple passes SGM
Raffaello Camoriano;Lorenzo Rosasco
2016-01-01
Abstract
We study the generalization properties of stochastic gradient methods for learning with convex loss functions and linearly parameterized functions. We show that, in the absence of penalizations or constraints, the stability and approximation properties of the algorithm can be controlled by tuning either the step-size or the number of passes over the data. In this view, these parameters can be seen to control a form of implicit regularization. Numerical results complement the theoretical findings.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
Generalization Properties.pdf
accesso aperto
Tipologia:
Documento in Post-print
Dimensione
378.13 kB
Formato
Adobe PDF
|
378.13 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.