Inverse consistency and global convergence of ResNets
- 👤 Speaker: Francois-Xavier Vialard (Université Gustave Eiffel) 🔗 Website
- 📅 Date & Time: Wednesday 01 June 2022, 14:00 - 15:00
- 📍 Venue: Virtual
Abstract
In this talk, I will discuss two very different applications related by the simple idea of invertible transformations.
- The first topic is an analysis of inverse consistency penalty in image matching in conjunction with the use of neural networks. We show that neural networks favours the emergence of smooth transformation for the inverse consistency. Experimentally, we show that this behaviour is fairly stable with respect to the chosen architecture. This is joint work with H. Greer, R. Kwitt and M. Niethammer.
-The second topic is an analysis of global convergence of residual networks when the residual block is parametrized via reproducing kernel Hilbert space vector field. We prove that the resulting problem satisfies the so-called Polyak-Lojasiewicz property, for instance ensuring global convergence if the iterates are bounded. We show that this property applies in a continuous limit as well as in the fully discrete setting. This is joint work with R. Barboni and G. Peyré.
Join Zoom Meeting https://maths-cam-ac-uk.zoom.us/j/94812219444?pwd=K00vZUVUU2NDbHozR2h1UzdLRlI1QT09
Meeting ID: 948 1221 9444 Passcode: 485548
Series This talk is part of the CCIMI Seminars series.
Included in Lists
- All CMS events
- All Talks (aka the CURE list)
- bld31
- Cambridge Centre for Data-Driven Discovery (C2D3)
- Cambridge talks
- CCIMI
- CCIMI Seminars
- Chris Davis' list
- CMS Events
- custom
- DPMMS info aggregator
- DPMMS lists
- DPMMS Lists
- Guy Emerson's list
- Hanchen DaDaDash
- Interested Talks
- ndk22's list
- ob366-ai4er
- rp587
- School of Physical Sciences
- Statistical Laboratory info aggregator
- Trust & Technology Initiative - interesting events
- Virtual
- yk449
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)



Wednesday 01 June 2022, 14:00-15:00