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 11th International Workshop on “Optimization for Machine Learning”, to be held as an independent event, co-located with NeurIPS. 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.
All accepted contributions will be listed on the workshop webpage (though there are no archival proceedings) and are expected to be presented as a poster during the workshop. A few submissions will in addition be selected for contributed talks or for short spotlight presentations.
The main topics are, including, but not limited to:
Nonconvex Optimization
-Local and global optimality theory
-The role of overparameterization
-Architecture dependent optimization techniques
-The interface of generalization and optimization
-Convex concave decompositions, D.C. programming
-Approximation Algorithms
-Other topics in nonconvex optimization
Stochastic, Parallel and Online Optimization:
-Large-scale learning, massive data sets
-Distributed and decentralized algorithms
-Distributed optimization algorithms, and parallel architectures
-Optimization using GPUs, Streaming algorithms
-Decomposition for large-scale, message-passing, and online optimization
-Stochastic approximations
Algorithms and Techniques (application oriented)
-Global and Lipschitz optimization
-Algorithms for nonsmooth optimization
-Linear and higher-order relaxations
-Polyhedral combinatorics applications to ML problems
Combinatorial Optimization
-Optimization in Graphical Models
-Structure learning
-MAP estimation in continuous and discrete random fields
-Clustering and graph-partitioning
-Semi-supervised and multiple-instance learning
-Other discrete optimization models and algorithms
Other optimization techniques
-Hashing based optimization, sketching techniques
-Optimization in statistics, statistical/computational tradeoffs
-Optimization on manifolds, metric spaces; optimal transport
-Polynomials, sums-of-squares, moment problems
-Optimization techniques for Reinforcement Learning
Numerical optimization
-Optimization software
-Integration with deep learning software, accelerator hardware and systems
-Crucial implementation details (architecture, language, etc.)
Looking forward to another great OPT workshop!