Preprint · 2023 · Open access
TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity
arXiv (Cornell University) · Published 10 November 2023 · DOI 10.48550/arxiv.2311.06205
In brief
“TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity” is a 2023 preprint by Kai Jia and Martin Rinard, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 1
- Most cited in
- 2024 (1)
- References
- 1
- Authors
- 2
Abstract
We present the Trust Region Adversarial Functional Subdifferential (TRAFS) algorithm for constrained optimization of nonsmooth convex Lipschitz functions. Unlike previous methods that assume a subgradient oracle model, we work with the functional subdifferential defined as a set of subgradients that simultaneously captures sufficient local information for effective minimization while being easy to compute for a wide range of functions. In each iteration, TRAFS finds the best step vector in an $\ell_2$-bounded trust region by considering the worst bound given by the functional subdifferential. TRAFS finds an approximate solution with an absolute error up to $ε$ in $\mathcal{O}\left( ε^{-1}\right)$ or $\mathcal{O}\left(ε^{-0.5} \right)$ iterations depending on whether the objective function is strongly convex, compared to the previously best-known bounds of $\mathcal{O}\left(ε^{-2}\right)$ and $\mathcal{O}\left(ε^{-1}\right)$ in these settings. TRAFS makes faster progress if the functional subdifferential satisfies a locally quadratic property; as a corollary, TRAFS achieves linear convergence (i.e., $\mathcal{O}\left(\log ε^{-1}\right)$) for strongly convex smooth functions. In the numerical experiments, TRAFS is on average 39.1x faster and solves twice as many problems compared to the second-best method.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Jia, K., & Rinard, M. (2023). TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.06205
MLA 9
Jia, Kai, and Martin Rinard. “TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity.” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2311.06205.
Chicago
Jia, Kai and Martin Rinard. 2023. “TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.06205.
Harvard
Jia, K. and Rinard, M. (2023) ‘TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity’, arXiv (Cornell University). doi:10.48550/arxiv.2311.06205.
IEEE
K. Jia and M. Rinard, “TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2311.06205.
BibTeX
@misc{jia2023trafs,
title = {{TRAFS: A Nonsmooth Convex Optimization Algorithm with \$\mathcal{O}\left(\frac{1}ε\right)\$ Iteration Complexity}},
author = {Jia, Kai and Rinard, Martin},
howpublished = {arXiv (Cornell University)},
year = {2023},
doi = {10.48550/arxiv.2311.06205},
url = {https://doi.org/10.48550/arxiv.2311.06205}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
- TRAF
- nonsmooth convex optimization
- trust region method
- iteration complexity
- Lipschitz functions
- strongly convex functions
- linear convergence
- constrained optimization
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Jia, K., & Rinard, M. (2023). TRAFS: A Nonsmooth Convex Optimization Algorithm with $\mathcal{O}\left(\frac{1}ε\right)$ Iteration Complexity. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.06205
How many times has this paper been cited?
1 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?
Kai Jia, Martin Rinard.
What is the DOI of this paper?
10.48550/arxiv.2311.06205. The permanent link is https://doi.org/10.48550/arxiv.2311.06205.
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.