Fwd: Thesis Proposal - May 5, 2023 - Cristian Challu - Representing Time: Towards Pragmatic Multivariate Time Series Models

[Artur Dubrawski]

As previously announced, more intellectual cameos are coming our way in the
first week of May.

Please mark your calendars for Cristian's thesis proposal talk:

Cheers
Artur


---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Wed, Apr 19, 2023 at 10:42 AM
Subject: Thesis Proposal - May 5, 2023 - Cristian Challu - Representing
Time: Towards Pragmatic Multivariate Time Series Models
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <ywu at stat.ucla.edu>


*Thesis Proposal*

Date: May 5, 2023
Time: 3:00pm (EST) (Remote only)

*Title: **Representing Time: Towards Pragmatic Multivariate Time Series
Models*
Abstract:
Time series models leverage temporal dependencies among observations and
interactions between multiple features in a data stream. During the last
decade, the unprecedented success of deep learning (DL), primarily in its
application to Computer Vision and Natural Language Processing, has slowly
but steadily permeated to time series analytics. From Recurrent Neural
Networks to Transformers, new advancements in architectural design improved
capabilities and performance. Despite this success, I identify several
challenges to the broader adoption of current state-of-the-art (SoTA) time
series models, including distribution shifts, missing data, computational
complexity, trustworthiness, and interpretability. The success of DL models
is usually justified by their ability to automatically discover helpful
data representations. We typically hope that multivariate time series
models, that involve high-dimensional objects with numerous time series and
temporal observations, exhibit useful temporal dependencies and
inter-feature relations. I propose to design new DL architectures and
algorithms for forecasting and anomaly detection tasks that leverage these
dependencies to induce efficient learning of representations capable of (i)
improving the models' performance, (ii) improving robustness by favoring
domain adaptation, and (iii) reducing overparameterization to improve
scalability. The already completed work includes five different models and
algorithms that achieve SoTA performance on relevant tasks and address a
few key adoption challenges. The proposed research extends that work in the
following directions: developing healthcare applications, analyzing the
enabling conditions for transfer learning between domains and tasks, and
extending prior work to multivariate long-horizon forecasting.

*Thesis Committee:*
Artur Dubrawski, Chair
Roni Rosenfeld
Barnabas Poczos
Ying Nian Wu (UCLA)

Link to the draft document:
https://drive.google.com/drive/u/3/folders/1fyyY_h9Ok3zk1a5KzTgsJNCq4mIRhh9G

Zoom meeting link:
https://cmu.zoom.us/j/92381510152?pwd=ZXk0Q0JaNlVVSk55a3RXZkM1c2ZYQT09

-- 
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/20230419/42306f94/attachment.html>