University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Practical issues for stochastic optimisation in Imaging

Practical issues for stochastic optimisation in Imaging

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact nobody.

RNTW01 - Rich and Nonlinear Tomography (RNT) in Radar, Astronomy and Geophysics

Stochastic optimisation methods have in recent years seen wide adoption for image reconstruction problems. These include variance reduction modifications to SGD (SVRG, SAGA ), primal dual algorithms (SPDHG), acceleration techniques, and many more, but the impact of hyperparameters and their limitations significantly affect their deploymenty in practical imaging problems. In this talk we will discuss practicalities in deploying these reconstruction algorithms in imaging problems, including medical tomography, and present some future directions.

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity