REMINDER: Thesis Proposal - May 3, 2023 - Ifigeneia Apostolopoulou - Decision-Making Under Latent Factors

[Artur Dubrawski]

Another reminder about another milestone talk.

Ifi, tomorrow late afternoon.

Zoom only.

See you all there.

Cheers,
Artur

On Sat, Apr 29, 2023 at 9:44 AM Artur Dubrawski <awd at cs.cmu.edu> wrote:

> And, to provide icing on the cake of multiple excellent Auton
> presentations next week, please mark your calendars for Ifi's doctoral
> thesis proposal talk on Wednesday.
>
> Cheers
> Artur
>
> ---------- Forwarded message ---------
> From: Diane Stidle <stidle at andrew.cmu.edu>
> Date: Fri, Apr 28, 2023 at 2:38 PM
> Subject: Thesis Proposal - May 3, 2023 - Ifigeneia Apostolopoulou -
> Decision-Making Under Latent Factors
> To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <fusi at microsoft.com>, <
> doucet at stats.ox.ac.uk>, <arnaud-doucet at google.com>
>
>
> *Thesis Proposal*
>
> Date: May 3, 2023
> Time: 3:30pm (EST) (Remote only)
> Speaker: Ifigeneia Apostolopoulou
>
> *Title: **Decision-Making Under Latent Factors*
>
> Abstract:
> Complex data arise in many fields including health care, neuroscience,
> computer vision, and many others. However, they often exhibit simple, yet
> unobserved patterns. These patterns can be represented by latent variables
> that augment the observations in the system of interest. This thesis
> surveys how to use latent variable models to guide decision-making. We
> approach decision-making as a workflow of three cognitive tasks: i)
> Representation Learning, ii) Temporal Modeling, iii) Uncertainty-Aware
> Reasoning. We propose that the processing ability required for each task
> can be improved by the use of latent variable models. To demonstrate that,
> we first discuss the types of patterns that latent variables need to
> capture for each task. Further, we develop inference tools that allow for
> expressive posterior distributions. Finally, our empirical analysis
> demonstrates the superior performance of latent variable models on several
> machine learning problems compared to their counterparts that operate
> purely in the observed data space.
>
> *Thesis Committee: *
> Artur Dubrawski (Chair)
> Ruslan Salakhutdinov
> Tom Mitchell
> Nicolo Fusi   (Microsoft)
> Arnaud Doucet (Google Deepmind)
>
> Zoom Link:
> https://cmu.zoom.us/j/96935140004?pwd=akNlbmU4TnRPWWlmWE5wWGIxaU5MZz09
>
>
> --
> Diane Stidle
> PhD Program Manager
> Machine Learning Department
> Carnegie Mellon Universitystidle at andrew.cmu.edu
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20230502/a9ba6eca/attachment.html>