Postdoc position at the Department of Mathematics and Mathematical Statistics, Umeå University, under the supervision of WASP Fellow Alp Yurtsever.
Project description and working tasks
The connection between optimization and machine learning is at the heart of many recent breakthroughs in artificial intelligence and autonomous systems. Many machine learning applications are modeled as optimization problems, and as problems become more and more complex, new optimization methods are needed. Within this framework, the successful candidate is encouraged to develop their research agenda in close collaboration with their supervisor. Potential areas of interest include, but are not limited to:
- Efficient and scalable algorithms for machine learning,
- Optimization problems with stochastic constraints,
- Implicit regularization in neural networks,
- Optimization with quantum computation,
- Distributed optimization and federated learning,
- Operator splitting methods in optimization,
- Continual learning,
- Bilevel optimization and applications in machine learning,
- Representation learning,
- Optimization on manifolds.