In this paper, we study the convergence of a block-coordinate incremental gradient method. Under some specific assumptions on the objective function, we prove that the block-coordinate incremental gradient method can be seen as a gradient method with errors and convergence can be proved by showing the error at each iteration satisfies some standard conditions. Thus, we can prove convergence towards stationary points when the block incremental gradient method is coupled with a diminishing stepsize and towards an epsilon-approximate solution when a bounded away from zero stepsize is employed.

On the convergence of a Block-Coordinate Incremental Gradient method / Palagi, Laura; Seccia, Ruggiero. - In: SOFT COMPUTING. - ISSN 1432-7643. - (2021), pp. 1-12. [10.1007/s00500-021-05695-4]

On the convergence of a Block-Coordinate Incremental Gradient method

Laura Palagi;Ruggiero Seccia
2021

Abstract

In this paper, we study the convergence of a block-coordinate incremental gradient method. Under some specific assumptions on the objective function, we prove that the block-coordinate incremental gradient method can be seen as a gradient method with errors and convergence can be proved by showing the error at each iteration satisfies some standard conditions. Thus, we can prove convergence towards stationary points when the block incremental gradient method is coupled with a diminishing stepsize and towards an epsilon-approximate solution when a bounded away from zero stepsize is employed.
2021
Incremental gradient; Block-coordinate decomposition; Online optimization
01 Pubblicazione su rivista::01a Articolo in rivista
On the convergence of a Block-Coordinate Incremental Gradient method / Palagi, Laura; Seccia, Ruggiero. - In: SOFT COMPUTING. - ISSN 1432-7643. - (2021), pp. 1-12. [10.1007/s00500-021-05695-4]
File allegati a questo prodotto
File Dimensione Formato  
Palagi_On-The-Convergence_2021.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 371.09 kB
Formato Adobe PDF
371.09 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1513147
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact