In this paper, we consider stochastic weakly convex optimization problems, however without the existence of a stochastic subgradient oracle. We present a derivative free algorithm that uses a two point approximation for computing a gradient estimate of the smoothed function. We prove convergence at a similar rate as state of the art methods, however with a larger constant, and report some numerical results showing the effectiveness of the approach.
A zeroth order method for stochastic weakly convex optimization
Rinaldi F.
2021
Abstract
In this paper, we consider stochastic weakly convex optimization problems, however without the existence of a stochastic subgradient oracle. We present a derivative free algorithm that uses a two point approximation for computing a gradient estimate of the smoothed function. We prove convergence at a similar rate as state of the art methods, however with a larger constant, and report some numerical results showing the effectiveness of the approach.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Kungurtsev-Rinaldi2021_Article_AZerothOrderMethodForStochasti(7).pdf
accesso aperto
Tipologia:
Published (Publisher's Version of Record)
Licenza:
Creative commons
Dimensione
2.53 MB
Formato
Adobe PDF
|
2.53 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
