From awd at cs.cmu.edu  Tue Apr  5 18:32:31 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Tue, 5 Apr 2022 18:32:31 -0400
Subject: Fwd: Thesis Proposal - April 18, 2022 - Kin Gutierrez Olivares -
 Applied Mathematics of the Future or the Future of Forecast
In-Reply-To: <fb86a2cb-75ed-377e-0cda-3aa64cce99f2@andrew.cmu.edu>
References: <fb86a2cb-75ed-377e-0cda-3aa64cce99f2@andrew.cmu.edu>
Message-ID: <CAJvAoyu_uF+TJhxAE8s_=wTh2Dk=sKtf=tmRw2TU804Hr_7v2g@mail.gmail.com>

Team,

Please mark your calendar for this classy event.

Cheers,
Artur

(PS Mononito: Do we want to consider it a fulfillment of our weekly
brainstorming session for that Monday?)





---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Tue, Apr 5, 2022 at 5:52 PM
Subject: Thesis Proposal - April 18, 2022 - Kin Gutierrez Olivares -
Applied Mathematics of the Future or the Future of Forecast
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <robstine at amazon.com>


*Thesis Proposal*

Date: April 18, 2022
Time: 1:30pm (EDT) (Remote)
Speaker: Kin Gutierrez Olivares

*Title: Applied Mathematics of the Future or the Future of Forecast*

Abstract:
Novel learning algorithms have enhanced our ability to acquire knowledge
solely from past observations of single events to learn from the
observations of several related events. This ability to leverage shared
useful information across time series is causing a paradigm shift in the
time-series forecasting practice.
In this proposed thesis, we aim to advance time-series forecasting methods
powered by machine learning and address some of the most pressing
challenges that limit usability, usefulness, and attainable real-world
impact of the existing technology, including human interpretability, the
ability to leverage structured information, generalization capabilities and
computational costs.

*Thesis Committee:*
Artur Dubrawski (Chair)
Barnabas Poczos
Russ Salakhutdinov
Robert A. Stine (Amazon)

Zoom Meeting link:
https://cmu.zoom.us/s/92165828919?pwd=b0dPUW1jNS9BeDA0NEZBTTBSUGhpQT09

Link to Draft Document:
https://drive.google.com/file/d/15hE6NapHCOEO0wxgvjLdv6XUhYLxAa3N/view?usp=sharing

-- 
Diane Stidle
Graduate Programs 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/20220405/506cb76b/attachment.html>

From awd at cs.cmu.edu  Fri Apr  8 13:02:00 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Fri, 8 Apr 2022 13:02:00 -0400
Subject: Fwd: PhD Speaking Qualifier: Kernel Density Decision Trees
In-Reply-To: <CADL7rvJWbWOCWypww0Zej42bzA+jTYCVPZ3j2R+TfGhYpjXyWg@mail.gmail.com>
References: <CADL7rvJWbWOCWypww0Zej42bzA+jTYCVPZ3j2R+TfGhYpjXyWg@mail.gmail.com>
Message-ID: <CAJvAoyvdR-T_Er44+pUm6QRibm2xxqdtu0DAeJ1NYTYPAGSjLg@mail.gmail.com>

fyi, if you have not seen this work from Jack, you've got to catch up!

Artur

---------- Forwarded message ---------
From: Jack Good <jhgood at cs.cmu.edu>
Date: Fri, Apr 8, 2022 at 12:46 PM
Subject: PhD Speaking Qualifier: Kernel Density Decision Trees
To: <ri-people at lists.andrew.cmu.edu>


Hi everyone,

I'll be presenting my speaking qualifier *Tuesday, April 19 at 10:00 am* on
Zoom. Everyone is welcome.

*Date: *Tuesday, April 19
*Time:* 10:00 am EDT
*Zoom: https://cmu.zoom.us/j/93872260456?pwd=SHVWRjZXTW9aZHB6U1lTWG9TUTcvUT09
<https://cmu.zoom.us/j/93872260456?pwd=SHVWRjZXTW9aZHB6U1lTWG9TUTcvUT09>*
*Meeting ID: *938 7226 0456
*Passcode: *790431

*Title: *Kernel Density Decision Trees

*Abstract*
We propose kernel density decision trees (KDDTs), a novel fuzzy decision
tree (FDT) formalism based on kernel density estimation that improves the
robustness of decision trees and ensembles and offers additional utility.
FDTs mitigate the sensitivity of decision trees to uncertainty by
representing uncertainty through fuzzy partitions. However, compared to
conventional, crisp decision trees, FDTs are generally complex to apply,
sensitive to design choices, slow to fit and make predictions, and
difficult to interpret. Moreover, finding the optimal threshold for a given
fuzzy split is challenging, resulting in methods that discretize data,
settle for near-optimal thresholds, or fuzzify crisp trees. Our KDDTs
address these shortcomings by representing uncertainty intuitively through
kernel distributions and by using a novel, scalable generalization of the
CART algorithm for finding optimal partitions for FDTs with
piecewise-linear splitting functions or KDDTs with piecewise-constant
fitting kernels. KDDTs can improve robustness to random or adversarial
perturbation, reduce or eliminate the need for ensemble methods, enable
smooth regression with trees, and give access to gradient-based feature
learning methods that can improve prediction performance and reduce model
complexity.

*Committee*
Artur Dubrawski (Chair)
Barnabas Poczos
Mario Berges
Nick Gisolfi
_______________________________________________
ri-people mailing list
ri-people at lists.andrew.cmu.edu
https://lists.andrew.cmu.edu/mailman/listinfo/ri-people
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220408/b31bf196/attachment.html>

From awd at cs.cmu.edu  Mon Apr 11 09:35:12 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 11 Apr 2022 09:35:12 -0400
Subject: Fwd: Reminder - Thesis Defense - April 11, 2022 - Maria Jahja -
 Sensor Fusion Frameworks for Nowcasting
In-Reply-To: <6d4958ea-07b9-cc5f-6327-05f13e05ea65@andrew.cmu.edu>
References: <6d4958ea-07b9-cc5f-6327-05f13e05ea65@andrew.cmu.edu>
Message-ID: <CAJvAoyvN-9mx0c2EEQ_dmgNADWp7dpG89ZcXgQNmx6=wNufvkg@mail.gmail.com>

This can be of interest to many of us.

Artur

---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Mon, Apr 11, 2022 at 9:22 AM
Subject: Reminder - Thesis Defense - April 11, 2022 - Maria Jahja - Sensor
Fusion Frameworks for Nowcasting
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <jsharpna at ucdavis.edu>


*Thesis Defense*

Date: April 11, 2022
Time: 2:30pm (EDT) (Remote)
PhD Candidate: Maria Jahja
                            (Statistics & Machine Learning PhD)

*Title: Sensor Fusion Frameworks for Nowcasting*
*Abstract:*
A fundamental task in many online time series settings is to estimate the
finalized value of a signal that will only be fully observed at a later
time. The goal in nowcasting is to produce such estimates using
contemporaneous information; this differs from the task of forecasting,
which learns from past data to predict future values. In this thesis, we
study sensor fusion (SF), a sequential nowcasting framework derived from a
process-agnostic Kalman filter (KF), and detail two (mathematically
equivalent) reformulations: first to the standard KF itself via an
augmented measurement space, and then to an equality-constrained regression
problem. We leverage these equivalences to port several established ideas
(e.g., regularization schemes) in regression to dynamical systems.

In settings where only convolved outcomes of the signal can be observed,
several new challenges arise: (i) deconvolution to infer the latent state,
(ii) subsequent uncertainty propagation through SF, and (iii) reconvolution
frameworks to evaluate performance. Towards solving these challenges, we
introduce new methodology to perform and evaluate real-time nowcasting by
deconvolution with specialized regularization techniques, which can prepend
the SF framework. We motivate our work throughout by applications to track
disease activity of influenza and COVID-19 in the United States.

*Thesis Committee:*
Ryan Tibshirani, Chair
Roni Rosenfeld
Val?rie Ventura
Larry Wasserman
James Sharpnack (UC Davis)

Zoom Meeting Link:
https://cmu.zoom.us/j/98710500061?pwd=SFJLUGFyMjg5ek9naU44K2tDeW90Zz09
Meeting ID: 987 1050 0061
Passcode: 434421

Link to Draft Document:
https://drive.google.com/file/d/13LD1fIF9dGNDH3mQgX1Au5Vxq4yXLARe/view?usp=sharing

-- 
Diane Stidle
Graduate Programs 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/20220411/36682213/attachment.html>

From awd at cs.cmu.edu  Mon Apr 18 10:19:24 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 18 Apr 2022 10:19:24 -0400
Subject: Fwd: Reminder - Thesis Proposal - April 18, 2022 - Kin Gutierrez
 Olivares - Applied Mathematics of the Future or the Future of Forecast
In-Reply-To: <689d47eb-1450-8eab-c60d-4009ed1f2b8b@andrew.cmu.edu>
References: <689d47eb-1450-8eab-c60d-4009ed1f2b8b@andrew.cmu.edu>
Message-ID: <CAJvAoysxhPTP3H=URJyT=Re=GLfrATpV-f68vdxg8=HFX_35QA@mail.gmail.com>

fun talk today!

---------- Forwarded message ---------
From: Diane Stidle <stidle at andrew.cmu.edu>
Date: Mon, Apr 18, 2022 at 9:58 AM
Subject: Reminder - Thesis Proposal - April 18, 2022 - Kin Gutierrez
Olivares - Applied Mathematics of the Future or the Future of Forecast
To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <robstine at amazon.com>


*Thesis Proposal*

Date: April 18, 2022
Time: 1:30pm (EDT) (Remote)
Speaker: Kin Gutierrez Olivares

*Title: Applied Mathematics of the Future or the Future of Forecast*

Abstract:
Novel learning algorithms have enhanced our ability to acquire knowledge
solely from past observations of single events to learn from the
observations of several related events. This ability to leverage shared
useful information across time series is causing a paradigm shift in the
time-series forecasting practice.
In this proposed thesis, we aim to advance time-series forecasting methods
powered by machine learning and address some of the most pressing
challenges that limit usability, usefulness, and attainable real-world
impact of the existing technology, including human interpretability, the
ability to leverage structured information, generalization capabilities and
computational costs.

*Thesis Committee:*
Artur Dubrawski (Chair)
Barnabas Poczos
Russ Salakhutdinov
Robert A. Stine (Amazon)

Zoom Meeting link:
https://cmu.zoom.us/s/92165828919?pwd=b0dPUW1jNS9BeDA0NEZBTTBSUGhpQT09

Link to Draft Document:
https://drive.google.com/file/d/15hE6NapHCOEO0wxgvjLdv6XUhYLxAa3N/view?usp=sharing

-- 
Diane Stidle
Graduate Programs 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/20220418/f94ff9eb/attachment.html>

From awd at cs.cmu.edu  Mon Apr 18 10:22:10 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 18 Apr 2022 10:22:10 -0400
Subject: Fwd: Miland Tambe on AI for Social Impact: Results from Deployments
 for Public Health and Conservation
In-Reply-To: <aae4610086c8b3a8646b00cbe.b5ed94badf.20220418135923.5eee78ea41.e5be2f0f@mail75.suw151.rsgsv.net>
References: <aae4610086c8b3a8646b00cbe.b5ed94badf.20220418135923.5eee78ea41.e5be2f0f@mail75.suw151.rsgsv.net>
Message-ID: <CAJvAoyu+0pmRMZPAzLu0vyC37aePEM7n6QjY==CL67MHq3p=-w@mail.gmail.com>

This can be worth attending by anyone interested in making a difference in
healthcare using AI.
Unfortunately I will have to miss - please let me know if you are planning
to attend and I'd be keen to ask you to share notes later.

Artur

---------- Forwarded message ---------
From: C3.ai Digital Transformation Institute <info at c3dti.ai>
Date: Mon, Apr 18, 2022 at 10:16 AM
Subject: Miland Tambe on AI for Social Impact: Results from Deployments for
Public Health and Conservation
To: <awd at cs.cmu.edu>


Miland Tambe on AI for Social Impact: Results from Deployments for Public
Health and Conservation
[image: C3DTI Colloquium on Digital Transformation Science]
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=f4067d174d&e=b5ed94badf>

The Colloquium on Digital Transformation is a series of weekly online talks
on how artificial intelligence, machine learning, and big data can lead to
scientific breakthroughs with large-scale societal benefit.


*See details of upcoming talks here
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=e910483357&e=b5ed94badf>
and
note we have the same Zoom Webinar registration
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=a97ae0a61e&e=b5ed94badf>
link
for all spring 2022 talks*

*Miland Tambe on AI for Social Impact: Results from Deployments for Public
Health and Conservation*

*April 21, 1 pm PT/3 pm CT*



*Miland Tambe, Gordon McKay Professor of Computer Science  Director of
Center for Research in Computation and Society Harvard University*

<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=4f5111df67&e=b5ed94badf>

With the maturing of AI and multi-agent systems research, we have a
tremendous opportunity to direct these advances towards addressing complex
societal problems. I will focus on domains of public health and
conservation, and address one key cross-cutting challenge: how to
effectively deploy our limited intervention resources in these problem
domains. I will present results from work around the globe using AI for
challenges such as HIV prevention, maternal and child care interventions,
as well as for wildlife conservation. Achieving social impact in these
domains often requires methodological advances. To that end, I will
highlight key research advances in multi-agent reasoning and learning, in
particular, restless multi-armed bandits, influence maximization in social
networks, computational game theory, and decision-focused learning. In
pushing this research agenda, our ultimate goal is to facilitate local
communities and nonprofits to directly benefit from advances in AI tools
and techniques.

Milind Tambe
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=3783a062d4&e=b5ed94badf>
is the Gordon McKay Professor of Computer Science and Director of the
Center for Research in Computation and Society at Harvard University; he
also directs "AI for Social Good" at Google Research India. He is the
recipient of the IJCAI John McCarthy Award, AAMAS ACM Autonomous Agents
Research Award, AAAI Robert S. Engelmore Memorial Lecture Award, and he is
a fellow of AAAI and ACM. He has also received the INFORMS Wagner prize,
Rist Prize from Military Operations Research Society, and Columbus
Fellowship Foundation Homeland Security Award, along with commendations
from the U.S. Coast Guard, Federal Air Marshals Service and Los Angeles
airport police.
*UPCOMING SPEAKERS
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=fd04bd61b9&e=b5ed94badf>*

April 28, 1 pm PT/3 pm CT
*Ruta Mehta*, Assistant Professor, University of Illinois at
Urbana-Champaign

May 5, 1 pm PT/3 pm CT
*Nikhil Garg*, Assistant Professor, Cornell Tech

*Watch for announcements of the next speaker series*


*Watch all C3.ai DTI talks on our YouTube channel*

YouTube.com/C3DigitalTransformationInstitute
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=fa669d60bd&e=b5ed94badf>

*The Science of Digital Transformation*

*About the C3.ai Digital Transformation Institute*

Established in March 2020 by C3 AI, Microsoft, and leading universities,
the C3.ai Digital Transformation Institute is a research consortium
dedicated to accelerating the socioeconomic benefits of artificial
intelligence. The Institute engages the world?s leading scientists to
conduct research and train practitioners in the new Science of Digital
Transformation, which operates at the intersection of artificial
intelligence, machine learning, cloud computing, internet of things, big
data analytics, organizational behavior, public policy, and ethics. The ten
C3.ai Digital Transformation Institute consortium member universities and
research laboratories are: University of Illinois at Urbana-Champaign;
University of California, Berkeley; Carnegie Mellon University; KTH Royal
Institute of Technology; Lawrence Berkeley National Laboratory;
Massachusetts Institute of Technology; National Center for Supercomputing
Applications at University of Illinois at Urbana-Champaign; Princeton
University; Stanford University; and University of Chicago. Learn more at
C3DTI.ai
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=3246416082&e=b5ed94badf>
.
[image: Twitter]
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=f956d6c4eb&e=b5ed94badf>
[image: LinkedIn]
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=0d5421aa1d&e=b5ed94badf>
[image: Facebook]
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=cae116e836&e=b5ed94badf>
[image: YouTube]
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=aa891afaef&e=b5ed94badf>
[image: Website]
<https://c3dti.us8.list-manage.com/track/click?u=aae4610086c8b3a8646b00cbe&id=145578362e&e=b5ed94badf>
[image: Email] <info at c3dti.ai>

*C3.ai Digital Transformation Institute @ Berkeley*
University of California, Berkeley
750 Sutardja Dai Hall, MC 1764
Berkeley, California 94720-1764

*C3.ai Digital Transformation Institute @ Illinois*
University of Illinois at Urbana-Champaign
1205 W. Clark Street, MC-257, Room 1008
Urbana, Illinois 61801
*Copyright ? 2022 C3.ai Digital Transformation Institute, All rights
reserved.*
You are receiving this email because you opted in via our website.

Want to change how you receive these emails?
You can update your preferences
<https://c3dti.us8.list-manage.com/profile?u=aae4610086c8b3a8646b00cbe&id=2aac18199b&e=b5ed94badf&c=5eee78ea41>
or
unsubscribe from this list
<https://c3dti.us8.list-manage.com/unsubscribe?u=aae4610086c8b3a8646b00cbe&id=2aac18199b&e=b5ed94badf&c=5eee78ea41>
.

[image: Email Marketing Powered by Mailchimp]
<http://www.mailchimp.com/email-referral/?utm_source=freemium_newsletter&utm_medium=email&utm_campaign=referral_marketing&aid=aae4610086c8b3a8646b00cbe&afl=1>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220418/3cb82041/attachment-0001.html>

From predragp at andrew.cmu.edu  Mon Apr 18 11:33:35 2022
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Mon, 18 Apr 2022 11:33:35 -0400
Subject: Unable to access /zfsauton/datasets
In-Reply-To: <CAErmj0p2mBMTre_-w=qxNNSeD=ds+UgD2z3LQ3y95sm5U=CLzw@mail.gmail.com>
References: <CAErmj0p2mBMTre_-w=qxNNSeD=ds+UgD2z3LQ3y95sm5U=CLzw@mail.gmail.com>
Message-ID: <CAEFFt-FuY2FukkEf5phsjhMrvC=D0Kf95eUCJKVAH_OF7q7C_g@mail.gmail.com>

I am aware. I am still investigating. The server stopped responding to ping
requests about an hour ago. I don't want to second guess but it looks as a
serious hardware issue. The server is 7 year old.

On Mon, Apr 18, 2022, 11:26 AM Swapnil Pande <swapnilp at andrew.cmu.edu>
wrote:

> Hi Predrag,
>
> Hope you're doing well.
>
> I am having trouble accessing datasets stored on `/zfsauton/datasets`.
> Running `ls` in /zfsauton seems to hang. Do you know what might be the
> problem?
>
> Thanks for your help!
>
> Regards,
> Swapnil
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220418/bc07c750/attachment.html>

From predragp at andrew.cmu.edu  Mon Apr 18 13:21:41 2022
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Mon, 18 Apr 2022 13:21:41 -0400
Subject: Unable to access /zfsauton/datasets
In-Reply-To: <CAEFFt-FuY2FukkEf5phsjhMrvC=D0Kf95eUCJKVAH_OF7q7C_g@mail.gmail.com>
References: <CAErmj0p2mBMTre_-w=qxNNSeD=ds+UgD2z3LQ3y95sm5U=CLzw@mail.gmail.com>
 <CAEFFt-FuY2FukkEf5phsjhMrvC=D0Kf95eUCJKVAH_OF7q7C_g@mail.gmail.com>
Message-ID: <CAEFFt-G07tSy9RDUsC7NqNigavirMgZYW37hKAiDwX9bxt=Fyw@mail.gmail.com>

/zfsauton/datasets are now available. I spoke too soon. The datasets NFS
shares are hosted on the largest file server (Ourea) we had in the lab
purchased 2.5 years ago by Dr. Schneider. That is a relatively new
hardware. The server rebooted and it took a long time to clear the file
system. I didn't find any reason for a reboot in the past 10-15 minutes
since the server came back on line and I had access to it.

I am not going to second guess today what was the problem. If one of the
PMx guys wants to join this forensic investigation they are more than
welcome.

Predrag

On Mon, Apr 18, 2022 at 11:33 AM Predrag Punosevac <predragp at andrew.cmu.edu>
wrote:

> I am aware. I am still investigating. The server stopped responding to
> ping requests about an hour ago. I don't want to second guess but it looks
> as a serious hardware issue. The server is 7 year old.
>
> On Mon, Apr 18, 2022, 11:26 AM Swapnil Pande <swapnilp at andrew.cmu.edu>
> wrote:
>
>> Hi Predrag,
>>
>> Hope you're doing well.
>>
>> I am having trouble accessing datasets stored on `/zfsauton/datasets`.
>> Running `ls` in /zfsauton seems to hang. Do you know what might be the
>> problem?
>>
>> Thanks for your help!
>>
>> Regards,
>> Swapnil
>>
>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220418/3399aee0/attachment.html>

From kdgutier at andrew.cmu.edu  Mon Apr 18 13:33:49 2022
From: kdgutier at andrew.cmu.edu (Kin Gutierrez Olivares)
Date: Mon, 18 Apr 2022 13:33:49 -0400
Subject: Reminder - Thesis Proposal - April 18, 2022 - Kin Gutierrez
 Olivares - Applied Mathematics of the Future or the Future of Forecast
In-Reply-To: <CAJvAoysxhPTP3H=URJyT=Re=GLfrATpV-f68vdxg8=HFX_35QA@mail.gmail.com>
References: <689d47eb-1450-8eab-c60d-4009ed1f2b8b@andrew.cmu.edu>
 <CAJvAoysxhPTP3H=URJyT=Re=GLfrATpV-f68vdxg8=HFX_35QA@mail.gmail.com>
Message-ID: <CA+WaLYuRQHpD8UN8poY=w3_CByb1vS48bi39Z9OHiBrs2FkopA@mail.gmail.com>

Hi all this is the pass code for the thesis proposal
629338

On Mon, Apr 18, 2022 at 10:21 AM Artur Dubrawski <awd at cs.cmu.edu> wrote:

> fun talk today!
>
> ---------- Forwarded message ---------
> From: Diane Stidle <stidle at andrew.cmu.edu>
> Date: Mon, Apr 18, 2022 at 9:58 AM
> Subject: Reminder - Thesis Proposal - April 18, 2022 - Kin Gutierrez
> Olivares - Applied Mathematics of the Future or the Future of Forecast
> To: ml-seminar at cs.cmu.edu <ML-SEMINAR at cs.cmu.edu>, <robstine at amazon.com>
>
>
> *Thesis Proposal*
>
> Date: April 18, 2022
> Time: 1:30pm (EDT) (Remote)
> Speaker: Kin Gutierrez Olivares
>
> *Title: Applied Mathematics of the Future or the Future of Forecast*
>
> Abstract:
> Novel learning algorithms have enhanced our ability to acquire knowledge
> solely from past observations of single events to learn from the
> observations of several related events. This ability to leverage shared
> useful information across time series is causing a paradigm shift in the
> time-series forecasting practice.
> In this proposed thesis, we aim to advance time-series forecasting methods
> powered by machine learning and address some of the most pressing
> challenges that limit usability, usefulness, and attainable real-world
> impact of the existing technology, including human interpretability, the
> ability to leverage structured information, generalization capabilities and
> computational costs.
>
> *Thesis Committee:*
> Artur Dubrawski (Chair)
> Barnabas Poczos
> Russ Salakhutdinov
> Robert A. Stine (Amazon)
>
> Zoom Meeting link:
> https://cmu.zoom.us/s/92165828919?pwd=b0dPUW1jNS9BeDA0NEZBTTBSUGhpQT09
>
> Link to Draft Document:
>
> https://drive.google.com/file/d/15hE6NapHCOEO0wxgvjLdv6XUhYLxAa3N/view?usp=sharing
>
> --
> Diane Stidle
> Graduate Programs 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/20220418/a482cd4d/attachment.html>

From predragp at andrew.cmu.edu  Mon Apr 18 15:41:17 2022
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Mon, 18 Apr 2022 15:41:17 -0400
Subject: Unable to access /zfsauton/datasets
In-Reply-To: <CAEFFt-G07tSy9RDUsC7NqNigavirMgZYW37hKAiDwX9bxt=Fyw@mail.gmail.com>
References: <CAErmj0p2mBMTre_-w=qxNNSeD=ds+UgD2z3LQ3y95sm5U=CLzw@mail.gmail.com>
 <CAEFFt-FuY2FukkEf5phsjhMrvC=D0Kf95eUCJKVAH_OF7q7C_g@mail.gmail.com>
 <CAEFFt-G07tSy9RDUsC7NqNigavirMgZYW37hKAiDwX9bxt=Fyw@mail.gmail.com>
Message-ID: <CAEFFt-EXUF=7_yy4TdD3xwOfPF6qRD0C3nC2VXrBUro_Pc0Ciw@mail.gmail.com>

In the case anybody cares, the crash was caused by the failing 12TB HDD.
The failing HDD caused ZFS to work overtime in order to recover errors
which in turn lead to the excessive use of memory. Once all 192GB of RAM
and 16 GB of swap were used, the server crashed.
Also in the case anyone cares, the solution was emailed to me by our
sysinfo log monitoring system. I just had to interpret it.

Best,
Predrag

On Mon, Apr 18, 2022 at 1:21 PM Predrag Punosevac <predragp at andrew.cmu.edu>
wrote:

> /zfsauton/datasets are now available. I spoke too soon. The datasets NFS
> shares are hosted on the largest file server (Ourea) we had in the lab
> purchased 2.5 years ago by Dr. Schneider. That is a relatively new
> hardware. The server rebooted and it took a long time to clear the file
> system. I didn't find any reason for a reboot in the past 10-15 minutes
> since the server came back on line and I had access to it.
>
> I am not going to second guess today what was the problem. If one of the
> PMx guys wants to join this forensic investigation they are more than
> welcome.
>
> Predrag
>
> On Mon, Apr 18, 2022 at 11:33 AM Predrag Punosevac <
> predragp at andrew.cmu.edu> wrote:
>
>> I am aware. I am still investigating. The server stopped responding to
>> ping requests about an hour ago. I don't want to second guess but it looks
>> as a serious hardware issue. The server is 7 year old.
>>
>> On Mon, Apr 18, 2022, 11:26 AM Swapnil Pande <swapnilp at andrew.cmu.edu>
>> wrote:
>>
>>> Hi Predrag,
>>>
>>> Hope you're doing well.
>>>
>>> I am having trouble accessing datasets stored on `/zfsauton/datasets`.
>>> Running `ls` in /zfsauton seems to hang. Do you know what might be the
>>> problem?
>>>
>>> Thanks for your help!
>>>
>>> Regards,
>>> Swapnil
>>>
>>>
>>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220418/c94fc118/attachment-0001.html>

From awd at cs.cmu.edu  Mon Apr 25 13:57:34 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 25 Apr 2022 13:57:34 -0400
Subject: Fwd: [AsilomarSSC] Asilomar SSC New Deadline: May 8, 2022
In-Reply-To: <ed0a665e-a902-4568-af2f-e8d85529b433@Spark>
References: <29ea0fde-9e9c-4868-b6ca-968ef81ec77b@Spark>
 <ed0a665e-a902-4568-af2f-e8d85529b433@Spark>
Message-ID: <CAJvAoyu2Rg9OthQau9JDdwJWZ6r_phJq485__PRgOxMvOYGzqw@mail.gmail.com>

Asilomar is a solid venue with a good reputation.
I believe a few chunks of our recent work could fit there nicely.

Artur



---------- Forwarded message ---------
From: Linda DeBrunner via AsilomarSSC <asilomarssc at lists.fsu.edu>
Date: Mon, Apr 25, 2022 at 1:55 PM
Subject: [AsilomarSSC] Asilomar SSC New Deadline: May 8, 2022
To: Linda DeBrunner via AsilomarSSC <asilomarssc at lists.fsu.edu>


*The new due date for Extended Summary submission for the Asilomar
Conference on Signals, Systems, and Computers is May 8, 2022. *The
conference will be held on Oct. 30-Nov. 2, 2022. We hope you will consider
submitting a paper. The Call for Papers is attached.

I have also included conference event planning information, which was
recently posted on the conference website: https://www.asilomarsscconf.org/

Best Regards,
Linda DeBrunner, PhD
Publicity Chair, Asilomar Conference on Signals, Systems, and Computers

Statement about the format of the conference events:

As we are preparing for the Asilomar Conference on Signals, Systems, and
Computers 2022, we would like to share our current planning efforts for the
2022 event.

COVID-19 has changed the way conference events can be planned. While our
small corner of CA is currently in the COVID-19 low-transmission category,
it is uncertain whether this will remain to be the case during Fall 2022.
As a result, our plan for this year is to again center the conference
around a virtual component. This ensures that all registered attendees will
be able to participate, irrespective of their geographical location or
health advisories in effect at the time of the conference.

In addition, the 2022 event will be complemented by a downscaled on-site
component held at the Asilomar conference grounds, where on-site attendees
will have the opportunity to present their work in a poster format.

What does this mean for your planning?

   - All authors will be required to upload a video presentation of their
   work by mid-September 2022. Video presentations will be available to
   registered attendees during October 2022 on our virtual platform.
   - The conference will take place from October 30th through November 2nd.
   During the morning hours (PST), a virtual component will take place on
   Gather.Town. Here, all of the authors and participants will interact in
   live poster sessions.
   - To be eligible for publication, all papers will need to have a video
   recording uploaded by early September 2022, and at least one author of each
   paper must be registered and participate in their assigned live poster
   session on Gather.Town.
   - In addition to the virtual event, our current plans are to offer a
   downscaled on-site component at the Asilomar Conference Grounds during the
   afternoons (PST). During this time, the on-site authors will present their
   posters a second time, this time to on-site attendees.
   - Unfortunately, it is very likely that we will have to restrict the
   number of on-site participants. Thus, authors of accepted papers will be
   polled for their preferences with respect to on-site/virtual attendance
   during early Summer. Only a subset among those willing to participate
   on-site will be provided with the opportunity to do so. The details on the
   selection procedure will be announced in time.

What are the potential caveats to attending on site?

   - The Asilomar Conference Grounds are a CA-State-owned facility and must
   adhere to all State constraints. We do not foresee the conference grounds
   to close its facilities at this time (as it did in 2020). However, there is
   always the slight chance it may do so should COVID-19 conditions worsen
   significantly in Fall 2022. Any interested participant should consider this
   issue when making travel arrangements.
   - All on-site attendees will be required (i) to strictly adhere to
   COVID-19 health and safety protocols in place at the time of the event, and
   (ii) to sign a release form and waiver of claims. Masks could be required
   at all times in indoor settings.
   - Attending the on-site event will NOT exempt the authors from the
   virtual participation requirement.


-- 
AsilomarSSC mailing list
AsilomarSSC at lists.fsu.edu
To Unsubscribe: https://lists.fsu.edu/mailman/listinfo/asilomarssc
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220425/e4c43a8f/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: call22_final_ext.pdf
Type: application/pdf
Size: 250498 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220425/e4c43a8f/attachment-0001.pdf>

From awd at cs.cmu.edu  Wed Apr 27 13:03:07 2022
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Wed, 27 Apr 2022 13:03:07 -0400
Subject: Fwd: [Imaging_ai_center_all] Workshop on Applications of Medical AI
 (AMAI)
In-Reply-To: <CH0PR08MB684214644C3A4C8013239A5AE9FA9@CH0PR08MB6842.namprd08.prod.outlook.com>
References: <CH0PR08MB684214644C3A4C8013239A5AE9FA9@CH0PR08MB6842.namprd08.prod.outlook.com>
Message-ID: <CAJvAoyuqp72HmQ+eV7kcV-_HHrpBm_CKo8b9ounfYBh1vWK7=w@mail.gmail.com>

Another venue to consider for our healthcare AI work.

Artur

---------- Forwarded message ---------
From: Wu, Shandong <wus3 at upmc.edu>
Date: Wed, Apr 27, 2022, 12:46 PM
Subject: [Imaging_ai_center_all] Workshop on Applications of Medical AI
(AMAI)
To: Imaging_AI_Center_All at list.pitt.edu <Imaging_AI_Center_All at list.pitt.edu
>


Hi All,

I am taking the lead of organizing the first workshop on Applications of
Medical AI (AMAI) that will take place on September 18, 2022, as a
satellite event of MICCAI2022 in Singapore. MICCAI is the premier
international conference in medical imaging and AI. AMAI calls for
submissions including full papers and abstracts. Accepted papers will be
published in Springer Lecture Notes in Computer Science and selected papers
will be invited for publication in the journal of Radiology: AI. Awards
will be given to best papers. Please consider submitting your work and
participation. CAIIMI (Pittsburgh Center for AI Innovation in Medical
Imaging) is supporting and sponsoring this workshop. I would also
appreciate you help spread the word about this workshop in your networks.
Please feel free to distribute the attached flyer and the full details of
AMAI can be found at this website:
https://sites.google.com/view/amai2022/home
<https://nam12.safelinks.protection.outlook.com/?url=https%3A%2F%2Furldefense.com%2Fv3%2F__https%3A%2F%2Fnam11.safelinks.protection.outlook.com%2F%3Furl%3Dhttps*3A*2F*2Fsites.google.com*2Fview*2Famai2022*2Fhome%26data%3D05*7C01*7Ckiftekha*40odu.edu*7Ce905563c73324f4378d508da2861207d*7C48bf86e811a24b8a8cb368d8be2227f3*7C0*7C1*7C637866694904373288*7CUnknown*7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0*3D*7C1000*7C*7C*7C%26sdata%3D5wYTdtnkcUhA5uI4jcTXHEXneN4aivI1lUn0qNizXTE*3D%26reserved%3D0__%3BJSUlJSUlJSUlJSUlJSUlJSUlJSUlJQ!!NHLzug!L87_jHrAzoiZPVAVcN9oaCg_NUgE0r8UWZPwXiAdf_559HkF27ogKpt7C4tYTodlHMdWq92pfMae-oKF%24&data=05%7C01%7CImaging_AI_Center_All%40list.pitt.edu%7Cf05cb50add6c41e736b308da286d32b8%7C9ef9f489e0a04eeb87cc3a526112fd0d%7C1%7C0%7C637866747872170852%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=WPhpgjxWzHfHOE7E0CNAGK1jYgTG0zanf83q1EICywU%3D&reserved=0>


Thanks,
Shandong

-- 
Shandong Wu, Ph.D.
Associate Professor of Radiology, Biomedical Informatics,
Bioengineering, Intelligent
Systems, Clinical and Translational Science,
Director, Intelligent Computing for Clinical Imaging (ICCI) Lab
Director, Pittsburgh Center for AI Innovation in Medical Imaging (
https://www.aimi.pitt.edu/)

Personal Zoom link: https://pitt.zoom.us/j/3980617026

Department of Radiology, University of Pittsburgh
Room 322, 3240 Craft Place, Pittsburgh, PA 15213
Tel:   412-641-2567
E-mail: wus3 at upmc.edu
Assistant to the Imaging AI Center: Amy Klym
E-mail: klymah at upmc.edu
Tel: 412-641-2566

_______________________________________________
Imaging_ai_center_all mailing list
Imaging_ai_center_all at list.pitt.edu
https://list.pitt.edu/mailman/listinfo/imaging_ai_center_all
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220427/a5d19302/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: AMAI2022_flyer.png
Type: image/png
Size: 714073 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20220427/a5d19302/attachment-0001.png>

From jeff4 at andrew.cmu.edu  Wed Apr 27 13:11:13 2022
From: jeff4 at andrew.cmu.edu (Jeff Schneider)
Date: Wed, 27 Apr 2022 13:11:13 -0400
Subject: Fwd: MSR Thesis Talk: Distributed Reinforcement Learning for
 Autonomous Driving
In-Reply-To: <CALnY40biAoMQCDkq+zpJ9iv-uObJ1KUu=P0bc-5euJ6JDo34pA@mail.gmail.com>
References: <CALnY40biAoMQCDkq+zpJ9iv-uObJ1KUu=P0bc-5euJ6JDo34pA@mail.gmail.com>
Message-ID: <4ed10d40-e94c-3878-17fe-cb4bfecc6411@andrew.cmu.edu>

Hi Everyone,

Please come and hear Zhe talk about his Masters work on parallelizing RL 
tomorrow!!

Jeff.



-------- Forwarded Message --------
Subject: 	MSR Thesis Talk: Distributed Reinforcement Learning for 
Autonomous Driving
Date: 	Wed, 20 Apr 2022 17:06:42 -0400
From: 	Zhe Huang <zhehuang at cmu.edu>
To: 	ri-people at cs.cmu.edu, Jeff Schneider <jeff4 at andrew.cmu.edu>, David 
Held <dheld at andrew.cmu.edu>, Adam Villaflor <avillafl at andrew.cmu.edu>, 
Barbara (B.J.) Fecich <barbarajean at cmu.edu>



Hello all,

I will be giving my MSR thesis talk on Thursday, April 28th, 2022 at 
1:30 pm EST. Everyone is invited!

*Date*: Thursday, April? 28th, 2022
*Time*: 1:30pm - 2pm
*Location*: NSH 4305, or
*Zoom Link*: https://cmu.zoom.us/j/8838971548 
<https://cmu.zoom.us/j/8838971548>

*Title*: Distributed Reinforcement Learning for Autonomous Driving

*Abstract*:

Due to the complex and safety-critical nature of autonomous driving, 
recent works typically test their ideas on simulators designed for the 
very purpose of advancing self-driving research. Despite the convenience 
of modeling autonomous driving as a trajectory optimization problem, few 
of these methods resort to online reinforcement learning (RL) to address 
challenging driving scenarios. This is mainly because classic online RL 
algorithms are originally designed for toy problems such as Atari games, 
which are solvable within hours. In contrast, it may take weeks or 
months to get satisfactory results on self-driving tasks using these 
online RL methods as a consequence of the time-consuming simulation and 
the difficulty of the problem itself. Thus, a promising online RL 
pipeline for autonomous driving should be efficiency driven.

In this thesis, we investigate the inefficiency of directly applying 
generic online RL algorithms to self-driving pipelines. We propose two 
distributed multi-agent RL algorithms, Multi-Parallel SAC (off-policy) 
and Multi-Parallel PPO (on-policy), both of which are highly scalable by 
running asynchronously. Our methods are dedicated to accelerating the 
online RL training on CARLA simulator by establishing both inter-process 
and intra-process parallelization. We demonstrate that our multi-agent 
methods achieve state-of-the-art performances on various CARLA 
self-driving tasks in much shorter and reasonable time.

*Committee*:
Prof. Jeff Schneider (advisor)
Prof. David Held
Adam Villaflor

--

Zhe Huang
MSR Student, Robotics Institute, CMU