DCL Seminar Series: Anthony Yezzi

Accelerated Optimization in the PDE Framework

No contact information submitted.
Sidebar Content
No sidebar content submitted.

Summary Sentence:

Accelerated Optimization in the PDE Framework

Full Summary:

Accelerated Optimization in the PDE Framework

  • Yezzi Yezzi


Following the seminal work of Nesterov, accelerated optimization methods 
(sometimes referred to as momentum methods) have been used to powerfully 
boost the performance of first-order, gradient-based parameter 
estimation in scenarios were second-order optimization strategies are 
either inapplicable or impractical. Not only does accelerated gradient 
descent converge considerably faster than traditional gradient descent, 
but it performs a more robust local search of the parameter space by 
initially overshooting and then oscillating back as it settles into a 
final configuration, thereby selecting only local minimizers with a 
attraction basin large enough to accommodate the initial overshoot. This 
behavior has made accelerated search methods particularly popular within 
the machine learning community where stochastic variants have been 
proposed as well.  So far, however, accelerated optimization methods 
have been applied to searches over finite parameter spaces. We show how 
a variational framework for these finite dimensional methods (recently 
formulated by Wibisono, Wilson, and Jordan) can be extended to the 
infinite dimensional setting and, in particular, to the manifold of 
planar curves in order to yield a new class of accelerated geometric, 
PDE-based active contours.


Professor Yezzi obtained both his Bachelor's degree and his Ph.D. in the Department of Electrical Engineering at the University of Minnesota with minors in mathematics and music.

After completing his Ph.D., he continued his research as a post-Doctoral Research Associate at the Laboratory for Information and Decision Systems at Massachusetts Institute of Technology in Boston, MA.

His research interests fall broadly within the fields of image processing and computer vision. In particular he is interested in curve and surface evolution theory and partial differential equation techniques as they apply to topics within these fields.

Much of Dr. Yezzi's work is particularly tailored to problems in medical imaging, including cardiac ultrasound, MRI, and CT. He joined the Georgia Tech faculty in the fall of 1999 where he has taught courses in DSP and is working to develop advanced courses in computer vision and medical image processing. 

Additional Information


Decision and Control Lab (DCL)

No categories were selected.
Related Core Research Areas
No core research areas were selected.
Newsroom Topics
No newsroom topics were selected.
DCL Seminar Series
  • Created By: mamstutz3
  • Workflow Status: Published
  • Created On: Oct 18, 2018 - 12:57pm
  • Last Updated: Oct 18, 2018 - 12:57pm