Preprint · 2026 · Open access

Primal-Dual Adaptive Subgradient Methods

Karthik Prakhya, Zimeng Wang, Alp Yurtsever

arXiv (Cornell University) · Published 20 October 2026 · DOI 10.48550/arxiv.2610.28300

Free PDFView at the publisherCite this paper

In brief

“Primal-Dual Adaptive Subgradient Methods” is a 2026 preprint by Karthik Prakhya and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
0
Authors
3

Abstract

We propose adaptive primal-dual subgradient methods for constrained convex optimization. Our first method applies an AdaGrad-style step-sizes to the dual problem and recovers primal solutions by averaging the associated Fenchel-type oracle outputs. It achieves $\widetilde{\mathcal{O}}(T^{-1/2})$ convergence for the dual objective residual, primal objective residual, and feasibility gap in the nonsmooth regime, while automatically improving to $\mathcal{O}(T^{-1})$ when the dual objective is smooth. We further develop an accelerated variant, which retains the $\widetilde{\mathcal{O}}(T^{-1/2})$ nonsmooth rate while achieving $\mathcal{O}(T^{-2})$ convergence in the smooth regime under mild assumptions. These guarantees require no prior knowledge of the underlying regularity. We demonstrate the empirical performance of the proposed methods on optimal transport and semidefinite relaxation of the Max-Cut problem.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Prakhya, K., Wang, Z., & Yurtsever, A. (2026). Primal-Dual Adaptive Subgradient Methods. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.28300

MLA 9

Prakhya, Karthik, et al. “Primal-Dual Adaptive Subgradient Methods.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.28300.

Chicago

Prakhya, Karthik, Zimeng Wang, and Alp Yurtsever. 2026. “Primal-Dual Adaptive Subgradient Methods.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.28300.

Harvard

Prakhya, K., Wang, Z. and Yurtsever, A. (2026) ‘Primal-Dual Adaptive Subgradient Methods’, arXiv (Cornell University). doi:10.48550/arxiv.2610.28300.

IEEE

K. Prakhya, Z. Wang, and A. Yurtsever, “Primal-Dual Adaptive Subgradient Methods,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.28300.

BibTeX

@misc{prakhya2026primal,
  title     = {{Primal-Dual Adaptive Subgradient Methods}},
  author    = {Prakhya, Karthik and Wang, Zimeng and Yurtsever, Alp},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.28300},
  url       = {https://doi.org/10.48550/arxiv.2610.28300}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques

  • adaptive step size
  • AdaGrad
  • constrained convex optimization
  • Fenchel duality
  • nonsmooth optimization
  • accelerated optimization
  • convergence rate
  • optimal transport

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Prakhya, K., Wang, Z., & Yurtsever, A. (2026). Primal-Dual Adaptive Subgradient Methods. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.28300

How many times has this paper been cited?

0 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Karthik Prakhya, Zimeng Wang, Alp Yurtsever.

What is the DOI of this paper?

10.48550/arxiv.2610.28300. The permanent link is https://doi.org/10.48550/arxiv.2610.28300.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.