[Colloquium] 8/31 Thesis Defense: Heejin Choi, TTIC

[Mary Marre via Colloquium]

 *Thesis Defense: Heejin Choi, TTIC*



*When:*      Friday, August 31st at *11:00am*

*Where:    * TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 526

*Who:        *Heejin Choi, TTIC


*Title:        *Efficient Structured Surrogate Loss and Regularization in
Structured Prediction


*Abstract:*
In this dissertation, we focus on several important problems in structured
prediction. In
structured prediction, the label has a rich intrinsic substructure, and the
loss varies with
respect to predicted label and the true label pair. Structured SVM is an
extension of binary
SVM to adapt to such structured tasks.

In the first part of the dissertation, we study the surrogate losses and
its efficient meth-
ods. To minimize the empirical risk, a surrogate loss which upper bounds
the loss, is used as a proxy to minimize the actual loss. Since the
objective function is written in terms of the surrogate loss, the choice of
the surrogate loss is important since the performance depends on it.
Another issue regarding the surrogate loss is the efficiency of the argmax
label inference for the surrogate loss. The efficiency is necessary for the
optimization since it is often the most time-consuming step. We present a
new class of surrogate losses named a bi-criteria surrogate loss, which is
a generalization of the popular surrogate losses. We first investigate an
efficient method for a slack rescaling formulation as a starting point
utilizing decomposability of the model. Then, we extend the algorithm for
the bi-criteria surrogate loss, which is very efficient and shows
performance improvement.

In the second part of the dissertation, another important issue of
regularization is studied. Specifically, we investigate a problem of
regularization in hierarchical classification when a structural imbalance
exists in the label structure. We present a method to normalize the
structure, as well as a new norm, namely shared Frobenius norm. It is
suitable for hierarchical classification that adapts to the data in
addition to the label structure.



*Thesis advisor:* Nathan Srebro <nati at ttic.edu>



Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 523*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20180828/2063155b/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 34245 bytes
Desc: not available
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20180828/2063155b/attachment-0001.png>