Università di Pisa
Sistema bibliotecario di ateneo

Convergence Analysis of Deflected Conditional Approximate Subgradient Methods

Giacomo, d'Antonio and Antonio, Frangioni (2009) Convergence Analysis of Deflected Conditional Approximate Subgradient Methods. SIAM Journal on Optimization, 20/200 (1). pp. 357-386. ISSN 1052-6234

Download (348Kb) | Preview


    Subgradient methods for nondifferentiable optimization benefit from deflection, i.e., defining the search direction as a combination of the previous direction and the current subgradient. In the constrained case they also benefit from projection of the search direction onto the feasible set prior to computing the steplength, that is, from the use of conditional subgradient techniques. However, combining the two techniques is not straightforward, especially if an inexact oracle is available which can only compute approximate function values and subgradients. We present a convergence analysis of several different variants, both conceptual and implementable, of approximate conditional deflected subgradient methods. Our analysis extends the available results in the literature by using the main stepsize rules presented so far while allowing deflection in a more flexible way. Furthermore, to allow for (diminishing/square summable) rules where the stepsize is tightly controlled a-priori, we propose a new class of deflection-restricted approaches where it is the deflection parameter, rather than the stepsize, which is dynamically adjusted using the "target value" of the optimization sequence. For both Polyak-type and diminishing/square summable stepsizes, we propose a "correction" of the standard formula which shows that, in the inexact case, knowledge about the error computed by the oracle (which is available in several practical applications) can be exploited in order to strengthen the convergence properties of the method. The analysis allows for several variants of the algorithm; at least one of them is likely to show numerical performances similar to these of "heavy ball" subgradient methods, popular within backpropagation approaches to train neural networks, while possessing stronger convergence properties.

    Item Type: Article
    Uncontrolled Keywords: Convex programming, Nondifferentiable Optimization, Subgradient methods, convergence analysis, Lagrangian relaxation, Backpropagation
    Subjects: Area01 - Scienze matematiche e informatiche > MAT/09 - Ricerca operativa
    Divisions: Dipartimenti (until 2012) > DIPARTIMENTO DI INFORMATICA
    Depositing User: Prof. Antonio Frangioni
    Date Deposited: 02 Jul 2009
    Last Modified: 20 Dec 2010 11:51
    URI: http://eprints.adm.unipi.it/id/eprint/601

    Repository staff only actions

    View Item