ABSTRACT:

I will discuss our recent work on stochastic optimization with equality constraints. We consider solving nonlinear optimization problems with stochastic objective and deterministic equality/inequality constraints. I will describe development of adaptive algorithms based on sequential quadratic programming and their properties.

Joint work with Sen Na, Yuchen Fang, Michael Mahoney, and Mihai Anitescu.

Preprints are available at:

https://arxiv.org/abs/2102.05320 (Published in Mathematical Programming)
https://arxiv.org/abs/2109.11502 (Published in Mathematical Programming)
https://arxiv.org/abs/2211.15943

BIO:

Mladen Kolar is Associate Professor of Econometrics and Statistics at the University of Chicago Booth School of Business. Kolar’s research is focused on high-dimensional statistical methods, probabilistic graphical models, and scalable optimization methods, driven by the need to uncover interesting and scientifically meaningful structures from observational data. His research appears in journals such as the Journal of Machine Learning Research, the Annals of Statistics, the Journal of the Royal Statistical Society, the Journal of the American Statistical Association, Biometrika, and other outlets. Kolar also regularly presents his research at the top machine learning conferences, including Advances in Neural Information Processing Systems (NeurIPS) and the International Conference of Machine Learning (ICML). Kolar currently serves as associate editor for the Journal of Machine Learning Research, the Journal of Computational and Graphical Statistics, and the New England Journal of Statistics in Data Science.

 Hosted by Professor Cho-Jui Hsieh