Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2503.07566 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912821849096192 |
|---|---|
| author | Zoll, Aaron Grimmer, Benjamin |
| author_facet | Zoll, Aaron Grimmer, Benjamin |
| contents | This paper proposes a universal algorithm for convex minimization problems of the composite form $g_0(x)+h(g_1(x),\dots, g_m(x)) + u(x)$. We allow each $g_j$ to independently range from being nonsmooth Lipschitz to smooth, from convex to strongly convex, described by notions of Hölder continuous gradients and uniform convexity. Note that, although the objective is built from a heterogeneous combination of such structured components, it does not necessarily possess smoothness, Lipschitzness, or any favorable structure overall other than convexity. Regardless, we provide a universal optimal method in terms of oracle access to (sub)gradients of each $g_j$. The key insight enabling our optimal universal analysis and a core technical contribution is the construction of two new constants, the Approximate Dualized Aggregate smoothness and strong convexity, which combine the benefits of each heterogeneous structure into single quantities amenable to analysis.
As a key application, fixing $h$ as the nonpositive indicator function, this model readily captures functionally constrained minimization $g_0(x)+u(x)$ subject to $g_j(x)\leq 0$. In particular, our algorithm and analysis are directly inspired by the smooth constrained minimization method of Zhang and Lan and consequently recover and generalize their accelerated guarantees. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Universally Optimal Primal-Dual Method for Minimizing Heterogeneous Compositions Zoll, Aaron Grimmer, Benjamin Optimization and Control This paper proposes a universal algorithm for convex minimization problems of the composite form $g_0(x)+h(g_1(x),\dots, g_m(x)) + u(x)$. We allow each $g_j$ to independently range from being nonsmooth Lipschitz to smooth, from convex to strongly convex, described by notions of Hölder continuous gradients and uniform convexity. Note that, although the objective is built from a heterogeneous combination of such structured components, it does not necessarily possess smoothness, Lipschitzness, or any favorable structure overall other than convexity. Regardless, we provide a universal optimal method in terms of oracle access to (sub)gradients of each $g_j$. The key insight enabling our optimal universal analysis and a core technical contribution is the construction of two new constants, the Approximate Dualized Aggregate smoothness and strong convexity, which combine the benefits of each heterogeneous structure into single quantities amenable to analysis. As a key application, fixing $h$ as the nonpositive indicator function, this model readily captures functionally constrained minimization $g_0(x)+u(x)$ subject to $g_j(x)\leq 0$. In particular, our algorithm and analysis are directly inspired by the smooth constrained minimization method of Zhang and Lan and consequently recover and generalize their accelerated guarantees. |
| title | A Universally Optimal Primal-Dual Method for Minimizing Heterogeneous Compositions |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2503.07566 |