Site menu:
OPT2022
We welcome you to participate in the 14th International OPT Workshop on Optimization for Machine Learning, to be held as a part of the NeurIPS 2022 conference. This year we particularly encourage (but not limit) submissions in the area of Reliable Optimization Methods for ML.
We are looking forward to an exciting in-person OPT!
Call for Participation
Important Dates
- Deadline for submission of papers: September 30, 2022 (AoE)*
- Notification of acceptance: October 20, 2022
- Presentation upload to slideslive: Nov 10, 2022)
- Camera-ready papers upload to openreview: Nov 10, 2022 (OPT2022 style file required)
- Poster upload to neurips website: Nov 27, 2022
- Workshop date: December 3, 2022
Invited Talks
- Niao He (ETH Zurich)
- Zico Kolter (CMU)
- Katya Scheinberg (Cornell)
- Aaron Sidford (Stanford)
Overview
Optimization lies at the heart of many machine learning algorithms and enjoys great interest in our community. Indeed, this intimate relation of optimization with ML is the key motivation for the OPT series of workshops. We aim to foster discussion, discovery, and dissemination of state-of-the-art research in optimization relevant to ML.
We invite participation in the 14th International (in-person) Workshop on "Optimization for Machine Learning", to be held as a part of the NeurIPS 2022 conference. We invite high quality submissions for presentation as spotlights or poster presentations during the workshop. We are especially interested in participants who can contribute theory / algorithms, applications, or implementations with a machine learning focus and encourage work-in-progress and state-of-art ideas.
AAll accepted contributions will be listed on the workshop webpage and are expected to be presented as a poster during the workshop. Given the online structure this year, we will ask each participant to submit their poster in advance of the workshop and be available during allotted time slots to answer questions. A few submissions will in addition be selected for contributed talks or for short spotlight presentations. We particularly encourage submissions in the area of Reliable Optimization Methods for ML.
The main topics are, including, but not limited to:
- Reliable Optimization Methods for ML
- Adaptive Stochastic Methods
- Approaches to Adversarial Machine Learning
- Average-case Analysis of Optimization Algorithms
- Deep learning optimizers
- Federated learning
- Games; min/max theory
- Nonconvex Optimization
- Privacy and Optimization
- The Interface of Generalization and Optimization
- Algorithms and techniques (higher-order methods, algorithms for nonsmooth problems, optimization with sparsity constraints, online optimization, streaming algorithms)
- Combinatorial optimization for machine learning
- Optimization software (integration with existing DL software, hardware accelerators and systems)
- Parallel and Distributed Optimization for large-scale learning
Submission Instructions:
- Submission website: OpenReview
- (Soft) Page limit: 5 pagesPlease use your own judgement. The submission should focus on the main contribution, additional results can be put into appendices. Please do not submit copies of your 9 page main conference submissions. Ultimately, the decision is at the reviewer's discretion.(without references and appendices)
- Submission format: Please use the OPT2022 style file for submission and CR version (and sharing on arxiv).
- Supplementary material: may be included, limited to a reasonable amount. Reviewers are not required to check the supplementary material, hence the paper should be self-contained.
- The submission must be sufficiently anonymized for double-blind reviewing.
- Dual submissions:
- We will not accept submissions that have already been accepted for publication in other venues with archival proceedings (including publications that will be presented at the NeurIPS main conference).
- We discourage dual submission to concurrent NeurIPS workshops, please choose the most suited workshop for your submission.
- Extended abstracts of papers under review at other conferences/journals can be submitted if this is ok for the conference/journal in question (if in doubt, please check with them first). Accepted papers will be posted on the webpage, but the workshop does not have archival proceedings.
Submission Instructions for Camera-Ready Version:
- Submission website: OpenReview
- Style file: the OPT2022 style file must be used
- Suggested page limit: 5-6 pages (without references and supplementary material). Please use your own judgement.
- Camera-Ready deadline: November 10, 2022
- Poster deadline: November 10, 2022
Looking forward to another great OPT workshop!
The Organizing Committee:
- John Duchi (Stanford)
- Quanquan Gu (UCLA)
- Cristóbal Guzmán (Pontificia Universidad Católica de Chile)
- Courtney Paquette (head) (McGill University)
- Sebastian Stich (CISPA Helmholtz Center for Information Security)