Fwd: Thesis Proposal - May 15th - Eric Lei - Multi-View Relationships for Analytics and Inference

[Artur Dubrawski]

Team,

Please come and cheer one of our own when they are making a decisive step
towards becoming "Doctor Lei"!

It will be practically next door (NSH 3002) at 10am this Wednesday.

Artur

---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Mon, May 13, 2019 at 10:26 AM
Subject: Thesis Proposal - May 15th - Eric Lei - Multi-View Relationships
for Analytics and Inference
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <labov1 at llnl.gov>, Mario
Berges <marioberges at cmu.edu>


*Thesis Proposal*

Date: May 15, 2019
Time: 10:00am
Place: NSH 3002
Speaker: Eric Lei

*Title: Multi-View Relationships for Analytics and Inference*

Abstract:
An interesting area of machine learning is methods for multi-view data.
Classical multi-view literature typically exploits multiple views to reduce
noise in data via conditional independence. However, the multi-view
relationships themselves are underutilized as factors for analyzing the
data. In this work, we investigate the usefulness of these relationships in
descriptive analytics and inference. In Part I, we cover a problem in
radiation detection about inference of latent variables that are shared
dependencies of multiple views. We show how the views can be aggregated by
filtering their inferences collectively using domain knowledge about their
relationships. In Part II, we address the problem of modeling multi-view
structure directly and applying such structure to descriptive analytics and
inference. We propose a method for radiation detection that learns linear
multi-view correlations and detects anomalies when these correlations are
disrupted. Next, we extend this idea to nonlinear multi-view correlations
by introducing a clustering method whose correlations are cluster-wise
linear. This method is applied to perform descriptive analytics on a
medical problem. Furthermore, we extend this work to classification and
demonstrate it on a load monitoring problem. Lastly, we propose an
extension to regression.
*Thesis Committee:*
Artur Dubrawski (Chair)
Barnabas Poczos
Mario Berges
Simon Labov (Lawrence Livermore National Laboratory)

Link to draft thesis document:
https://www.dropbox.com/s/uhl0swsodthsbw3/main1.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/20190513/7a0b6f41/attachment.html>