Let's congratulate our newest Doctors (and prepare for more to come soon!)

[Artur Dubrawski]

Dear Autonians,

We have reached what appears to be the new high in the production rate of
doctors coming out of our Auton Lab production lines.

So, recently, we have had these outstanding individuals graduating with
their Ph.D.s:

Dr. Karen Chen - on her way to become a professor at the University of
Maryland

Dr. Maria De Arteaga - on her way to become a processor at the University
of Texas

Dr. Chao Liu - on his way to become a researcher at Nvidia

Please join me in congratulating Karen, Maria and Chao on their remarkable
accomplishments
(and please strictly remember to address each of them by "Doctor" from now
on).

But, behold, we are not done yet!

Please mark your calendars as one more exciting thesis defense is coming.
This one is by Yichong Xu (he will be on his way to Microsoft Research
afterwards).
See below for details.

Cheers,
Artur

*Thesis **Defense*

Date: June 29, 2020
Time: 9:00am (EDT)
PhD Candidate: Yichong Xu

Virtual Presentation Link:
https://cmu.zoom.us/j/99909151454

*Title:  *Learning and Decision Making from Diverse Forms of Information

Abstract:
Classical machine learning posits that data are independently and
identically distributed, in a single format usually the same as test data.
In modern applications however, additional information in other formats
might be available freely or at a lower cost. For example, in data
crowdsourcing we can collect preferences over the data points instead of
directly asking the labels of a single data point at a lower cost. In
natural language understanding problems, we might have limited amount of
data in the target domain, but can use a large amount of general domain
data for free.

The main topic of this thesis is to study how to efficiently incorporate
these diverse forms of information into the learning and decision making
process. We study two representative paradigms in this thesis. Firstly, we
study learning and decision making problems with direct labels and
comparisons. Our algorithms can efficiently combine comparisons with direct
labels so that the total learning cost can be greatly reduced. Secondly, we
study multi-task learning problems from multiple domain data, and design
algorithms to transfer the data from a general, abundant domain to the
target domain. We show theoretical guarantees of our algorithms as well as
their statistical minimaxity through information-theoretic limits. On the
practical side, we demonstrate promising experimental results on price
estimation and natural language understanding tasks.

*Thesis Committee:*
Artur Dubrawski, Co-Chair
Aarti Singh, Co-Chair
Sivaraman Balakrishnan
John Langford (Microsoft Research)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20200615/cbbd0a5a/attachment.html>