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 13th International (Virtual) Workshop on "Optimization for Machine Learning", to be held as a part of the NeurIPS 2021 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.

All 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 Beyond Worst-case Complexity.

The main topics are, including, but not limited to:

- Average-case Analysis of Optimization Algorithms
- The Interface of Generalization and Optimization
- Adaptive Stochastic Methods
- Nonconvex Optimization
- Parallel and Distributed Optimization for large-scale learning, Federated Learning
- 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)

Submission instructions on the website, https://opt-ml.org/.