Abs-Smooth Frank-Wolfe Method: Primal-Dual Analysis, Heavy Ball Momentum, and Inexact Oracles
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914580463091712 |
|---|---|
| author | Tadinada, Sri Harshitha Pokutta, Sebastian Walther, Andrea |
| author_facet | Tadinada, Sri Harshitha Pokutta, Sebastian Walther, Andrea |
| contents | We study projection-free optimization for convex objectives that satisfy abs-smoothness, a structural property that captures many non-smooth yet piecewise smooth functions arising, e.g., in modern machine learning models. We develop a unified framework for Abs-Smooth Frank-Wolfe methods, establishing a clean primal-dual analysis that guarantees convergence without requiring classical smoothness assumptions. Our framework extends the available results in two important directions. First, we introduce a heavy ball momentum variant and show that momentum can be incorporated naturally under abs-smoothness while preserving convergence guarantees. Second, we analyze inexact minimization oracles, demonstrating robustness to approximate inner solutions. Moreover, we relax the full convexity assumption and study the case where convexity holds only for the piecewise linear approximations of the objective, further broadening the applicability of conditional gradient methods to a wider class of non-smooth problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19828 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Abs-Smooth Frank-Wolfe Method: Primal-Dual Analysis, Heavy Ball Momentum, and Inexact Oracles Tadinada, Sri Harshitha Pokutta, Sebastian Walther, Andrea Optimization and Control We study projection-free optimization for convex objectives that satisfy abs-smoothness, a structural property that captures many non-smooth yet piecewise smooth functions arising, e.g., in modern machine learning models. We develop a unified framework for Abs-Smooth Frank-Wolfe methods, establishing a clean primal-dual analysis that guarantees convergence without requiring classical smoothness assumptions. Our framework extends the available results in two important directions. First, we introduce a heavy ball momentum variant and show that momentum can be incorporated naturally under abs-smoothness while preserving convergence guarantees. Second, we analyze inexact minimization oracles, demonstrating robustness to approximate inner solutions. Moreover, we relax the full convexity assumption and study the case where convexity holds only for the piecewise linear approximations of the objective, further broadening the applicability of conditional gradient methods to a wider class of non-smooth problems. |
| title | Abs-Smooth Frank-Wolfe Method: Primal-Dual Analysis, Heavy Ball Momentum, and Inexact Oracles |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2605.19828 |