Metraipolis › archive › dc_dc6f20bd48e0

Synthesis of the Transient Behaviour of Optimization Algorithms for Strongly Convex Objective Functions — arXiv:2610.23206

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23206
License (as archived)
CC0-1.0
Archived
2026-10-19T09:37:46.280Z
SHA-256 of the archived text
4f6bd3f247d19dd69f32082c6df78701b8a5b2c2d0ff1f1fdd002d5c6db4e1d3
Stable URL of this page
https://metraipolis.com/documento/dc_dc6f20bd48e0

How to cite

Synthesis of the Transient Behaviour of Optimization Algorithms for Strongly Convex Objective Functions — arXiv:2610.23206 — arXiv (en), https://arxiv.org/abs/2610.23206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc6f20bd48e0 (Metraipolis archive dc_dc6f20bd48e0, sha256 4f6bd3f247d19dd69f32082c6df78701b8a5b2c2d0ff1f1fdd002d5c6db4e1d3)
BibTeX
@misc{dcdc6f20bd48e0,
  title = {Synthesis of the Transient Behaviour of Optimization Algorithms for Strongly Convex Objective Functions — arXiv:2610.23206},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23206},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc6f20bd48e0; sha256 4f6bd3f247d19dd69f32082c6df78701b8a5b2c2d0ff1f1fdd002d5c6db4e1d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the transient behavior of first-order optimization methods for unconstrained minimization of smooth and strongly convex objective functions. These methods are modelled as linear systems over finite-time intervals embedded in feedback with the gradient nonlinearity. By characterizing the function class through discrete-time Zames-Falb integral quadratic constraints, we employ a robust $\mathcal{H}_2$ control framework to obtain convex semidefinite programs certifying tight worst-case bounds on the terminal distance to the optimizer. Building on the same formulation, we derive a convex synthesis procedure for a transient-optimal method that achieves the optimal finite-horizon bounds and guarantees error reduction over any prescribed number of steps. The framework naturally extends to delayed gradient measurements, enabling both transient performance analysis and synthesis of optimal algorithms under feedback delays.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.23206 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:33:44.737Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).