Bibliothek

feed icon rss

Ihre E-Mail wurde erfolgreich gesendet. Bitte prüfen Sie Ihren Maileingang.

Leider ist ein Fehler beim E-Mail-Versand aufgetreten. Bitte versuchen Sie es erneut.

Vorgang fortführen?

Exportieren
Filter
Datenquelle
Erscheinungszeitraum
Sprache
  • 11
    Publikationsdatum: 2023-11-03
    Beschreibung: The most important ingredient for solving mixed-integer nonlinear programs (MINLPs) to global ϵ-optimality with spatial branch and bound is a tight, computationally tractable relaxation. Due to both theoretical and practical considerations, relaxations of MINLPs are usually required to be convex. Nonetheless, current optimization solvers can often successfully handle a moderate presence of nonconvexities, which opens the door for the use of potentially tighter nonconvex relaxations. In this work, we exploit this fact and make use of a nonconvex relaxation obtained via aggregation of constraints: a surrogate relaxation. These relaxations were actively studied for linear integer programs in the 70s and 80s, but they have been scarcely considered since. We revisit these relaxations in an MINLP setting and show the computational benefits and challenges they can have. Additionally, we study a generalization of such relaxation that allows for multiple aggregations simultaneously and present the first algorithm that is capable of computing the best set of aggregations. We propose a multitude of computational enhancements for improving its practical performance and evaluate the algorithm’s ability to generate strong dual bounds through extensive computational experiments.
    Sprache: Englisch
    Materialart: article , doc-type:article
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 12
    Publikationsdatum: 2023-12-14
    Beschreibung: Deep learning has received much attention lately due to the impressive empirical performance achieved by training algorithms. Consequently, a need for a better theoretical understanding of these problems has become more evident and multiple works in recent years have focused on this task. In this work, using a unified framework, we show that there exists a polyhedron that simultaneously encodes, in its facial structure, all possible deep neural network training problems that can arise from a given architecture, activation functions, loss function, and sample size. Notably, the size of the polyhedral representation depends only linearly on the sample size, and a better dependency on several other network parameters is unlikely. Using this general result, we compute the size of the polyhedral encoding for commonly used neural network architectures. Our results provide a new perspective on training problems through the lens of polyhedral theory and reveal strong structure arising from these problems.
    Sprache: Englisch
    Materialart: article , doc-type:article
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
  • 13
    Publikationsdatum: 2024-03-14
    Sprache: Englisch
    Materialart: article , doc-type:article
    Bibliothek Standort Signatur Band/Heft/Jahr Verfügbarkeit
    BibTip Andere fanden auch interessant ...
Schließen ⊗
Diese Webseite nutzt Cookies und das Analyse-Tool Matomo. Weitere Informationen finden Sie hier...