Sábháilte in:
| Príomhchruthaitheoirí: | , |
|---|---|
| Formáid: | Preprint |
| Foilsithe / Cruthaithe: |
2024
|
| Ábhair: | |
| Rochtain ar líne: | https://arxiv.org/abs/2403.02530 |
| Clibeanna: |
Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!
|
| _version_ | 1866913915657519104 |
|---|---|
| author | Olikier, Guillaume Waldspurger, Irène |
| author_facet | Olikier, Guillaume Waldspurger, Irène |
| contents | This paper considers the projected gradient descent (PGD) algorithm for the problem of minimizing a continuously differentiable function on a nonempty closed subset of a Euclidean vector space. Without further assumptions, this problem is intractable and algorithms are only expected to find a stationary point. PGD generates a sequence in the set whose accumulation points are known to be Mordukhovich stationary. In this paper, these accumulation points are proven to be Bouligand stationary, and even proximally stationary if the gradient is locally Lipschitz continuous. These are the strongest stationarity properties that can be expected for the considered problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02530 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Projected gradient descent accumulates at Bouligand stationary points Olikier, Guillaume Waldspurger, Irène Optimization and Control Numerical Analysis 65K10, 49J53, 90C26, 90C30, 90C46 This paper considers the projected gradient descent (PGD) algorithm for the problem of minimizing a continuously differentiable function on a nonempty closed subset of a Euclidean vector space. Without further assumptions, this problem is intractable and algorithms are only expected to find a stationary point. PGD generates a sequence in the set whose accumulation points are known to be Mordukhovich stationary. In this paper, these accumulation points are proven to be Bouligand stationary, and even proximally stationary if the gradient is locally Lipschitz continuous. These are the strongest stationarity properties that can be expected for the considered problem. |
| title | Projected gradient descent accumulates at Bouligand stationary points |
| topic | Optimization and Control Numerical Analysis 65K10, 49J53, 90C26, 90C30, 90C46 |
| url | https://arxiv.org/abs/2403.02530 |