PhD Thesis Proposal: Chirag Nagpal - Wednesday, December 15, 2021 (6pm)

[Artur Dubrawski]

Team,

We will have a pleasure to watch Chirag give his thesis proposal talk in
less than an hour. When the time comes, I recommend that you grab your
dinners, sit comfortably in front of your computer screens, and enjoy the
talk.

See below for the zoom link, etc.

Cheers
Artur

---------- Forwarded message ---------
From: Stacey Young <StaceyYoung at cmu.edu>
Date: Mon, Dec 6, 2021 at 4:45 PM
Subject: LTI PhD Thesis Proposal: Chirag Nagpal - Wednesday, December 15,
2021 (6pm)
To: <lti-students at cs.cmu.edu>, <lti-staff at cs.cmu.edu>, LTI-faculty-all <
lti-faculty-all at cs.cmu.edu>


The LTI is proud to announce the following PhD Thesis Proposal:

Leveraging Heterogeneity in Time-to-Event Predictions

Chirag Nagpal

Wednesday, December 15, 2021
6:00pm via Zoom
<https://cmu.zoom.us/j/93544413242?pwd=SkJIVW5vMkdoMVdHUnpWSzVtZ0t1Zz09>
*ID*: 93544413242
*Password*: 024906

*Committee:*

Artur Dubrawski, Robotics Institute, (Chair)
Louis-Philippe Morency
Bhiksha Ramakrishnan
Russell Greiner, (University of Alberta)
Katherine Heller, (Duke University and Google Research)

*Abstract:*

Time-to-Event Regression, often referred to as Survival Analysis or
Censored Regression involves learning of statistical estimators of the
survival distribution of an individual given their covariates. As opposed
to standard regression, survival analysis is challenging as it involves
accounting for outcomes censored due to loss of follow up. This
circumstance is common in, e.g., bio-statistics, predictive maintenance,
and econometrics. With the recent advances in machine learning methodology,
especially deep learning, it is now possible to exploit expressive
representations to help model survival outcomes. My thesis contributes to
this new body of work by demonstrating that problems in survival analysis
often manifest inherent heterogeneity which can be effectively discovered,
characterized, and modeled to learn better estimators of survival.
Heterogeneity may arise in a multitude of settings in the context of
survival analysis. Some examples include heterogeneity in the form of input
features or covariates (for instance, static vs. streaming, time-varying
data), or multiple outcomes of simultaneous interest (more commonly
referred to as competing risks). Other sources of heterogeneity involve
latent subgroups that manifest different base survival rates or diverse
responses to an intervention or treatment. Additional sources of
heterogeneity involve shifts in the covariate or outcome distributions at
the time of model deployment, exacerbating risk of mis-estimation.
Furthermore, heterogeneity may manifest in the outcomes of protected
demographics, especially if group membership information is not available
or misreported.
In this thesis, I aim to demonstrate that carefully modelling the inherent
structure of heterogeneity can boost predictive power of survival analysis
models while improving their specificity and precision of estimated
survival at an individual level. An overarching methodological framework of
this thesis is the application of graphical models to impose inherent
structure in time-to-event problems that explicitly model heterogeneity,
while employing advances in deep learning to learn powerful representations
of data that help leverage various aspects of heterogeneity.

A copy of the thesis proposal can be found here
<https://drive.google.com/file/d/1-uQ0w5x-zoY6mSXrU3aahGW2VWEAoLdJ/view>.



-- 

Stacey L. Young
PhD Academic Program Manager
LTI PhD Program, LTI Dual PhD/Portugal Program
LTI Minor/Concentration & Admin Support Robert Frederking
Language Technologies Institute
Pronouns she/her
Black Lives Matter

6415 Gates Hillman Complex
5000 Forbes Avenue
Pittsburgh, PA 15213

T: (412)268-2623
F: (412)268-6298

*Office Hours:
**Remote: *M-TH, 10am-5:30pm*
In Person:* F, 10am-5:30pm



-- 

*Chirag Nagpal* PhD Student, Auton Lab
School of Computer Science
Carnegie Mellon University
cs.cmu.edu/~chiragn
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20211215/ad62e096/attachment.html>