BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Mean field theory in Inverse Problems: from Bayesian inference to 
 overparameterization of networks - Qin Li (University of Wisconsin-Madison
 )
DTSTART:20211110T170000Z
DTEND:20211110T183000Z
UID:TALK165568@talks.cam.ac.uk
DESCRIPTION:Bayesian sampling and neural networks are seemingly two differ
 ent machine learning areas\, but they both deal with many particle systems
 . In sampling\, one evolves a large number of samples (particles) to match
  a target distribution function\, and in optimizing over-parameterized neu
 ral networks\, one can view neurons particles that feed each other informa
 tion in the DNN flow. These perspectives allow us to employ mean-field the
 ory\, a powerful tool that translates dynamics of many particle system int
 o a partial differential equation (PDE)\, so rich PDE analysis techniques 
 can be used to understand both the convergence of sampling methods and the
  zero-loss property of over-parameterization of ResNets. We showcase the u
 se of mean-field theory in these two machine learning areas\, and we also 
 invite the audience to brainstorm other possible applications..\n&nbsp\;
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR