University of Cambridge > Talks.cam > CCIMI Seminars > Finding stationary points on the bounded-rank variety: a geometric hurdle and a smooth workaround

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Finding stationary points on the bounded-rank variety: a geometric hurdle and a smooth workaround

Download to your calendar using vCal

If you have a question about this talk, please contact Hamza Fawzi .

The set of matrices of a certain size and rank is a smooth manifold. Unfortunately, it is not closed: this is uncomfortable for optimization. The closure of that manifold, namely, the set of matrices with bounded rank, is an algebraic variety but it is not smooth. That also is uncomfortable for optimization. Case in point, the norm of the (projected) gradient of the cost function can go to zero along a sequence even if the limit point of the sequence is not stationary. This can trick algorithms. I will characterize the geometry of this phenomenon. Then, I will discuss how lifting the problem to a smooth manifold makes it possible to converge to stationary points with certainty under mild conditions.

Joint work with Eitan Levin (CalTech) and Joe Kileel (UT Austin).

This talk is part of the CCIMI Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

MR12 DAMTP and online UK is new travel destination Cambridge University Engineering Department, LR2

Other talks

Cambridge RNA Club - ONLINE Tea and Coffee Break Paediatric Medicine and Rheumatology Quantifying the unquantifiable? Assessing the importance of almsgiving in early modern France and Spain Content, Caching and Kubernetes: Performance and User Experience in the Browser Studying viruses to understand what makes pandemic viruses special and how innate immunity works
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity