Return to Colloquia & Seminar listing
Optimization Methods for Machine Learning
Mathematics of Data & Decisions| Speaker: | Roummel Marcia, UC Merced |
| Location: | Zoom |
| Start time: | Tue, May 5 2020, 4:00PM |
Machine learning (ML) problems are often posed as highly nonlinear and nonconvex unconstrained optimization problems. Methods for solving ML problems based on stochastic gradient descent generally require fine-tuning many hyper-parameters. In this talk we discuss alternative approaches for solving ML problems based on a quasi-Newton trust-region framework that does not require extensive parameter tuning. We will present numerical results that demonstrate the potential of the proposed approaches.
Password for ZOOM meeting can be obtained from the organizer deloera@math.ucdavis.edu