From awd at cs.cmu.edu  Mon Apr  1 10:01:30 2024
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 1 Apr 2024 10:01:30 -0400
Subject: Fwd: Reminder - Thesis Defense - April 2, 2024 - Cristian Challu -
 Representing Time: Towards Pragmatic Multivariate Time Series Modeling
In-Reply-To: <f517369b-4bb1-465c-8447-60dee183e114@andrew.cmu.edu>
References: <f517369b-4bb1-465c-8447-60dee183e114@andrew.cmu.edu>
Message-ID: <CAJvAoyvZk4TDJDK=-8rciWkqvfyarvfoFmM2NOkAaqLok2Et7A@mail.gmail.com>

Team,

I saw Cristian practice his talk twice already, but I did not have enough
yet!
I am really looking forward to his final presentation tomorrow, it will be
fun and worth your time.

See you all there tomorrow.

Cheers
Artur

---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Mon, Apr 1, 2024 at 9:44?AM
Subject: Reminder - Thesis Defense - April 2, 2024 - Cristian Challu -
Representing Time: Towards Pragmatic Multivariate Time Series Modeling
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <ywu at stat.ucla.edu>


*Thesis Defense*

Date: April 2, 2024
Time: 11:00am (EDT)
Place: NSH 3305 & Remote
PhD Candidate: Cristian Challu

*Title: Representing Time: Towards Pragmatic Multivariate Time Series
Modeling*

Abstract:
Time series models are specialized in learning temporal dependencies among
observations and interactions between features in a data stream. During the
last decade, the unprecedented success of deep learning models on Computer
Vision and Natural Language Processing has steadily permeated to time
series tasks. From Recurrent Neural Networks to Transformers, new
advancements in architectural design improved capabilities and performance.
Despite this success, I identify several challenges to adopting current
state-of-the-art methods, including handling distribution shifts and
missing data, computational complexity, and interpretability.
The success of DL models is usually explained by their ability to
automatically discover helpful data representations. Multivariate time
series models involve high-dimensional objects with numerous time series
and temporal observations. However, they often exhibit strong temporal
dependencies and inter-feature relations. In this thesis, I propose to
design algorithms for forecasting and anomaly detection tasks that leverage
these dependencies to induce efficient learning of representations that
satisfy desirable properties that can (i) improve the models' performance,
(ii) improve robustness by favoring domain adaptation, and (iii) reduce
overparameterization to improve scalability. The completed work includes
three parts, presenting seven models and algorithms that achieve SoTA
performance in various tasks while addressing key adoption challenges.

In the first part, I explore the dynamic latent space principle and design
latent temporal representations to make robust anomaly detection and
forecasting models. In the second part, I present a novel scalable and
interpretable model for multi-step forecasting based on a non-linear
frequency decomposition with connections to Wavelet theory. It also
features two extensions on using multivariate exogenous covariates for
high-impact domains, including energy and healthcare. Finally, in the third
part, I present a large-scale study on enabling conditions, on both model
design and data characteristics, for transferability of pre-trained models
on time series tasks.

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

Link to Draft Document:
https://drive.google.com/file/d/17luIWYw3bLRYe-BuXn1QstlQad0ozXu8/view?usp=sharing

Zoom meeting link:
https://cmu.zoom.us/j/99919622332?pwd=Y0E0ZU0xMCswbmFyTXBzNDRuK05mZz09

Meeting ID: 999 1962 2332
Passcode: 902254

-- 
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/20240401/4a00dce7/attachment.html>

From awd at cs.cmu.edu  Tue Apr  2 18:00:49 2024
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Tue, 2 Apr 2024 18:00:49 -0400
Subject: Just if you did not get enough of talking about time series yet...
Message-ID: <CAJvAoyvqfpSoXVuP3TJagCi8ZiKjBUz-Y3KfOdxAx3JetY3ohw@mail.gmail.com>

...Mononito will be speaking on time series foundation models, and
specifically about the MOMENT family of models he led development of, at a
webinar hosted by Gradient AI tomorrow at 1pm.

Here's the invitation:
https://www.linkedin.com/events/timeseriesai-momentmodel7179687106024263680/theater/

Cheers,
Artur
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240402/2382c0d1/attachment.html>

From jeff4 at andrew.cmu.edu  Wed Apr 10 13:04:03 2024
From: jeff4 at andrew.cmu.edu (Jeff Schneider)
Date: Wed, 10 Apr 2024 13:04:03 -0400
Subject: Adam's defense today at 3pm in GHC 4405
In-Reply-To: <CAGW4BtyTmppyGuR7LUj5xoV-1RLaAMkDpPrqBDFWqqf7im8CbQ@mail.gmail.com>
References: <CAGW4BtyTmppyGuR7LUj5xoV-1RLaAMkDpPrqBDFWqqf7im8CbQ@mail.gmail.com>
Message-ID: <3bb4ba80-8514-0703-ea51-76599274ba03@andrew.cmu.edu>


Please come to Adam Villaflor's defense today.  Details are below:

For those of you who are on the CMU campus, this presentation will be in 
*GHC 4405.* For those attending remotely, the presentation will be on 
Zoom at

https://cmu.zoom.us/j/97014388887?pwd=bFlMRXl2NFVRZzBYRlJWNGxnNFBQQT09 
<https://cmu.zoom.us/j/97014388887?pwd=bFlMRXl2NFVRZzBYRlJWNGxnNFBQQT09>




From awd at cs.cmu.edu  Wed Apr 10 13:22:54 2024
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Wed, 10 Apr 2024 12:22:54 -0500
Subject: Fwd: rankings aren't everything, but...
In-Reply-To: <CAAZSyQ98h0v5R9P3AdZi56rKC6wNd9XNi8C04OkkqyiaNuoSgw@mail.gmail.com>
References: <CAAZSyQ98h0v5R9P3AdZi56rKC6wNd9XNi8C04OkkqyiaNuoSgw@mail.gmail.com>
Message-ID: <CAJvAoys5FGyj3gNYP3gAtu0cdrArcStLWBR93yjMUL61FVZ5cw@mail.gmail.com>

Not sure if you had seen this already, but either way rest assured the
Auton Lab has contributed to this.

Cheers
Artur

---------- Forwarded message ---------
From: Tom Mitchell <tommmitchell at gmail.com>
Date: Wed, Apr 10, 2024, 11:50?AM
Subject: rankings aren't everything, but...
To: <ml-all at cs.cmu.edu>


despite the fact that rankings of CS programs are always debatable, it's
nice to see the new US News & World Report rankings of CS programs,
released just two days ago:
[image: image.png]

Congratulations everybody in being part of the number one Machine Learning
Department, in the number one AI University!

Tom

-- 
Tom M. Mitchell
Founders University Professor
Machine Learning Department
Carnegie Mellon University
www.cs.cmu.edu/~tom
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240410/720e39f4/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 517439 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240410/720e39f4/attachment-0001.png>

From jeff4 at andrew.cmu.edu  Thu Apr 11 09:19:05 2024
From: jeff4 at andrew.cmu.edu (Jeff Schneider)
Date: Thu, 11 Apr 2024 09:19:05 -0400
Subject: Please come to Ian Char's PhD thesis defense starting at 10am in GHC
 6115!
In-Reply-To: <46ee1e64-06d3-4b2b-a4b4-f1c68bd5feb9@andrew.cmu.edu>
References: <46ee1e64-06d3-4b2b-a4b4-f1c68bd5feb9@andrew.cmu.edu>
Message-ID: <52e02621-9ea9-5810-8eb7-38c2dadd5a97@andrew.cmu.edu>




-------- Forwarded Message --------
Subject: 	Thesis Defense - April 11, 2024 - Ian Char - Advancing 
Model-Based Reinforcement Learning with Applications in Nuclear Fusion
Date: 	Thu, 28 Mar 2024 14:16:52 -0400
From: 	Diane Stidle <stidle at andrew.cmu.edu>
Reply-To: 	stidle at andrew.cmu.edu
To: 	ml-seminar at cs.cmu.edu <ML-SEMINAR at CS.CMU.EDU>, 
riedmiller at google.com, ekolemen at pppl.gov



*/Thesis?Defense/*

Date: April 11, 2024
Time: 10:00am (EDT)
Place: GHC 6115 & Remote
PhD Candidate: Ian Char

*Title: Advancing Model-Based Reinforcement Learning with Applications 
in Nuclear Fusion*

Abstract:

Reinforcement learning (RL) may be the key to overcoming previous 
insurmountable obstacles, leading to technological and scientific 
innovations. One such example where RL could have a sizable impact is in 
tokamak control. Tokamaks are one of the most promising devices for 
making nuclear fusion into a viable energy source. They operate by 
magnetically confining a plasma; however, sustaining the plasma for long 
periods of time and at high pressures remains a challenge for the 
tokamak control community. RL may be able to learn how to sustain the 
plasma, but like many exciting applications of RL, it is infeasible to 
collect data on the real device in order to learn a policy.

In this thesis, we explore learning policies using surrogate models of 
the environment, and especially using surrogate models that are learned 
from an offline data source. To start in Part I, we investigate the 
scenario in which one has access to a simulator that can be used to 
generate data, but the simulator is too computationally taxing to use 
data-hungry deep RL algorithms. We instead suggest a Bayesian 
optimization algorithm to learn such a policy. Following this, we pivot 
to the setting in which surrogate models of the environment can be 
learned with offline data. While these models are much more 
computationally cheap, their predictions inevitably contain errors. As 
such, both robust policy learning procedures and good uncertainty 
quantification of model errors are crucial for success. To address the 
former, in Part II we propose a trajectory stitching algorithm that 
accounts for these modeling errors and a policy network architecture 
that is adaptive, yet robust. Part III shifts focus onto uncertainty 
quantification, where we propose a more intelligent uncertainty sampling 
procedure and a neural process architecture for learning uncertainties 
efficiently. In the final part, we detail how we learned models to 
predict plasma evolution, how we used these models to train a neutral 
beam controller, and the results of deploying this controller on the 
DIII-D tokamak.

*Thesis?Committee:*
Jeff Schneider, Chair
Ruslan Salakhutdinov
Zico Kolter
Martin Riedmiller (DeepMind)
Egemen Kolemen (Princeton)

Link to Draft Document: 
https://drive.google.com/file/d/1VQAZDuvRA1GfEfZkGS6EfzFd-zovetU1/view?usp=sharing

Link to Zoom meeting:
https://www.google.com/url?q=https://cmu.zoom.us/j/94461753500?pwd%3DN1FmTktDWWU5cDkwM0szWWxvSXNndz09&sa=D&source=calendar&ust=1712067446243633&usg=AOvVaw0pAS1H8u4VyGICh2A69iS2 
<https://www.google.com/url?q=https://cmu.zoom.us/j/94461753500?pwd%3DN1FmTktDWWU5cDkwM0szWWxvSXNndz09&sa=D&source=calendar&ust=1712067446243633&usg=AOvVaw0pAS1H8u4VyGICh2A69iS2>

-- 
Diane Stidle
PhD Program Manager
Machine Learning Department
Carnegie Mellon University
stidle at andrew.cmu.edu


From predragp at andrew.cmu.edu  Mon Apr 15 11:22:33 2024
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Mon, 15 Apr 2024 09:22:33 -0600
Subject: RIP on June 30th RHEL 7 and Python 2
Message-ID: <CAEFFt-GB8=zD3y7fL_Vf+3S2WEGDXQ_rB3m6HZqkqpUC9QxqJw@mail.gmail.com>

It is official IBM is pulling a plug on RHEL 7 and Python 2. All scripts
and servers should be converted to RHEL 8 and Python 3 or shutdown by June
30th of this year. RHEL is yet to be approved for use in most government
agencies but we have been using it for since its release in June of 2022.


Best,
Predrag
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240415/1154fdb8/attachment.html>

From awd at cs.cmu.edu  Wed Apr 17 20:00:07 2024
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Wed, 17 Apr 2024 20:00:07 -0400
Subject: Auton Lab in Pittsburgh Post Gazette
Message-ID: <CAJvAoyvJ38PwcxPjG-sPChjMoKVsc_-bS9d-=008+1Xmd3dENA@mail.gmail.com>

Dear Autonians,

Check this out:
https://www.post-gazette.com/news/health/2024/04/14/documentary-pittsburgh-catching-medical-errors-the-pitch-patient-safety/stories/202404140031

Congrats to our EDS-HAT project team.

Cheers
Artur
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240417/a2572da1/attachment.html>

From awd at cs.cmu.edu  Mon Apr 22 09:51:50 2024
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 22 Apr 2024 09:51:50 -0400
Subject: Fwd: RI Ph.D. Thesis Proposal: Mononito Goswami
In-Reply-To: <CAPfXyxKmFDSco50XKtyKQFruN9k00ix4QhOCZKRHfCTuqkr4vw@mail.gmail.com>
References: <CAPfXyxKmFDSco50XKtyKQFruN9k00ix4QhOCZKRHfCTuqkr4vw@mail.gmail.com>
Message-ID: <CAJvAoysT6psxs6x5tG07xA-t9P1D4JCHipPGpYWpoORF5vwmOg@mail.gmail.com>

Team, please mark your calendars for Mononito's upcoming thesis proposal
talk.

Cheers
Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Mon, Apr 22, 2024, 9:47?AM
Subject: RI Ph.D. Thesis Proposal: Mononito Goswami
To: RI People <ri-people at andrew.cmu.edu>


Date: 01 May 2024
Time: 2:00 PM (ET)
Location: NSH 1305

Zoom Link:
https://cmu.zoom.us/j/97119194168?pwd=Uzd4cXFzTHRuZWU1RVJwb1JOMHU0UT09

Type: Ph.D. Thesis Proposal
Who: Mononito Goswami
Title: Towards Pragmatic Time Series Intelligence


Abstract:

The widespread adoption of time series machine learning (ML) models faces
multiple challenges involving data, modeling and evaluation.

*Data.* Modern ML models depend on copious amounts of cohesive and reliably
annotated data for training and evaluation. However, labeled data is not
always available and reliable, and can also be dispersed across different
locations. We propose systematic solutions to making time series data
ML-ready.

*Modeling.* Most current time series ML models are built, trained and
evaluated on individual datasets from a specific application domain. Thus,
to build an effective model for a particular application scenario,
substantial effort, time, and domain expertise are required to develop a
successful task-specific design. We propose to partially address this
limitation by developing large pre-trained foundation models for time
series, to ease development of useful models across diverse application
domains with limited resources, data and labels.

*Evaluation.* Currently, time series models are commonly evaluated using
relatively small, specific and highly tailored benchmarks, which may
obfuscate assessment of their performance. We highlight the gaps in
evaluation techniques and propose addressing the most important of them
through comprehensive, multi-metric assessment.

In summary, this thesis aims to democratize time series artificial
intelligence by simplifying and accelerating development of models, while
improving their performance in real-world application scenarios facing
resource constraints and imperfect data.

Thesis Committee Members:
Artur Dubrawski, Chair
Jean Oh
Barnabas Pocz?s
Frederic Sala, University of Wisconsin-Madison
Laurent Callot, Amazon


A draft of the thesis proposal document is available at:

https://drive.google.com/drive/folders/1yzdjxg0Koj92msch3kRxJDemi29E9Snj?usp=sharing
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240422/aca6ed88/attachment.html>

From pbartosi at andrew.cmu.edu  Tue Apr 23 00:10:27 2024
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Tue, 23 Apr 2024 00:10:27 -0400
Subject: File servers maintenance
Message-ID: <CAN_-bZKok_zXJjWmOfEn_fOYjWeBEL62FMiPioW+hUGTMmTd2A@mail.gmail.com>

Hello.

On Friday [4/26/2024] afternoon our file servers: Uranus, Gaia and Ourea
will be taken offline for system upgrade. The whole operation should take
several hours.
During that time folders /zfsauton2 /data /project etc... will be
inaccessible.

Piotr.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240423/d76106d8/attachment.html>

From awd at cs.cmu.edu  Sat Apr 27 10:32:18 2024
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Sat, 27 Apr 2024 10:32:18 -0400
Subject: Karen Chen receives the prestigious NSF CAREER award
Message-ID: <CAJvAoyu4J6Y3iH1CODddLbzyKu6EaCSjcCX5sDW0yF1=UZX9rw@mail.gmail.com>

Team,

Please join me in congratulating our own Professor Chen for this important
highlight of her academic career.

https://www.nsf.gov/awardsearch/showAward?AWD_ID=2339674&HistoricalAwards=false

Way to go Karen!

Cheers,
Artur
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240427/10aac5bc/attachment.html>

From predragp at andrew.cmu.edu  Sun Apr 28 01:15:13 2024
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Sun, 28 Apr 2024 01:15:13 -0400
Subject: File servers maintenance
In-Reply-To: <CAN_-bZKok_zXJjWmOfEn_fOYjWeBEL62FMiPioW+hUGTMmTd2A@mail.gmail.com>
References: <CAN_-bZKok_zXJjWmOfEn_fOYjWeBEL62FMiPioW+hUGTMmTd2A@mail.gmail.com>
Message-ID: <CAEFFt-EP15phdxbg6sL-LW2LfHuzK2N22R1J1PsE8VvDtej6cw@mail.gmail.com>

Necessary OS upgrades/patches, pkg upgrades and  other preventive
maintenance work has been completed on all Auton Lab file servers and jail
hosts. As of an hour ago, the system is in normal operation mode.

Best,
Predrag

On Tue, Apr 23, 2024 at 12:11?AM Piotr Bartosiewicz <pbartosi at andrew.cmu.edu>
wrote:

> Hello.
>
> On Friday [4/26/2024] afternoon our file servers: Uranus, Gaia and Ourea
> will be taken offline for system upgrade. The whole operation should take
> several hours.
> During that time folders /zfsauton2 /data /project etc... will be
> inaccessible.
>
> Piotr.
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240428/e4a7bc65/attachment.html>

From kelenber at andrew.cmu.edu  Mon Apr 29 13:29:10 2024
From: kelenber at andrew.cmu.edu (Kimberly Elenberg)
Date: Mon, 29 Apr 2024 13:29:10 -0400
Subject: Karen Chen receives the prestigious NSF CAREER award
In-Reply-To: <CAJvAoyu4J6Y3iH1CODddLbzyKu6EaCSjcCX5sDW0yF1=UZX9rw@mail.gmail.com>
References: <CAJvAoyu4J6Y3iH1CODddLbzyKu6EaCSjcCX5sDW0yF1=UZX9rw@mail.gmail.com>
Message-ID: <CAHycrtN+9eGtmzb+KoSwWSVzg18syZEqELVtoEa=FFKfSKuQag@mail.gmail.com>

Amazing and well deserved recognition!! Best Regards, Kimberly

On Sat, Apr 27, 2024 at 10:33?AM Artur Dubrawski <awd at cs.cmu.edu> wrote:

> Team,
>
> Please join me in congratulating our own Professor Chen for this important
> highlight of her academic career.
>
>
> https://www.nsf.gov/awardsearch/showAward?AWD_ID=2339674&HistoricalAwards=false
>
> Way to go Karen!
>
> Cheers,
> Artur
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20240429/fdf16625/attachment.html>