Fwd: Thesis Proposal - Nov. 14, 2019 - Yichong Xu - Learning and Decision Making from Diverse Forms of Information

[Artur Dubrawski]

Dear Autonians,

Please come and enjoy an exceptional opportunity to learn about learning
from diverse forms of information from Yichong, who will be presenting his
thesis proposal this Thursday at 1pm in GHC 4405.

Cheers
Artur


---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Fri, Nov 1, 2019 at 3:12 PM
Subject: Thesis Proposal - Nov. 14, 2019 - Yichong Xu - Learning and
Decision Making from Diverse Forms of Information
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <jcl at microsoft.com>


*Thesis Proposal*

Date: November 14, 2019
Time: 1:00pm (EST)
Place: GHC 4405
Speaker: Yichong Xu

*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)

Link to the draft document:
https://www.dropbox.com/s/6r6qk3d7hkfkl8p/proposal.pdf?dl=0

-- 
Diane Stidle
Graduate Programs Manager
Machine Learning Department
Carnegie Mellon Universitystidle at cmu.edu
412-268-1299
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20191112/7f5bfe2e/attachment.html>