Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Adeoye, Adeyemi D."'
We present EGN, a stochastic second-order optimization algorithm that combines the generalized Gauss-Newton (GN) Hessian approximation with low-rank linear algebra to compute the descent direction. Leveraging the Duncan-Guttman matrix identity, the p
Externí odkaz:
http://arxiv.org/abs/2405.14402
The generalized Gauss-Newton (GGN) optimization method incorporates curvature estimates into its solution steps, and provides a good approximation to the Newton method for large-scale optimization problems. GGN has been found particularly interesting
Externí odkaz:
http://arxiv.org/abs/2404.14875
Autor:
Adeoye, Adeyemi D., Bemporad, Alberto
We introduce a notion of self-concordant smoothing for minimizing the sum of two convex functions, one of which is smooth and the other may be nonsmooth. The key highlight of our approach is in a natural property of the resulting problem's structure
Externí odkaz:
http://arxiv.org/abs/2309.01781
Autor:
Adeoye, Adeyemi D., Bemporad, Alberto
Optimization problems that include regularization functions in their objectives are regularly solved in many applications. When one seeks second-order methods for such problems, it may be desirable to exploit specific properties of some of these regu
Externí odkaz:
http://arxiv.org/abs/2112.07344
Autor:
Adeoye, Adeyemi D.1 (AUTHOR) adeyemi.adeoye@imtlucca.it, Bemporad, Alberto1 (AUTHOR)
Publikováno v:
Computational Optimization & Applications. Nov2023, Vol. 86 Issue 2, p599-626. 28p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.