From predragp at andrew.cmu.edu  Wed Dec  2 14:08:33 2020
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Wed, 02 Dec 2020 14:08:33 -0500
Subject: servers down?
In-Reply-To: <CABwU0nmcE5044mXeZT4Geknz97J3X6Oju6=6GFPiMY6hPSmMQQ@mail.gmail.com>
References: <CABwU0nmcE5044mXeZT4Geknz97J3X6Oju6=6GFPiMY6hPSmMQQ@mail.gmail.com>
Message-ID: <20201202190833.OCx4m%predragp@andrew.cmu.edu>

Ifigeneia Apostolopoulou <iapostol at andrew.cmu.edu> wrote:

> Hi Predrag,
> 
> long time no see :)
> are the servers down? also I can't login to any of them.

They are not down. They have to be regularly maintained which means that
sometimes they have to be rebooted with a new kernel. I just rebooted
the main file server. The reboot of the large file server takes about 5
min. 

Cheers,
Predrag

> 
> Could not chdir to home directory /zfsauton3/home/iapostol: No such file or
> directory

From ngisolfi at cs.cmu.edu  Thu Dec  3 11:30:50 2020
From: ngisolfi at cs.cmu.edu (Nick Gisolfi)
Date: Thu, 3 Dec 2020 11:30:50 -0500
Subject: [Lunch] Today @noon over Zoom
Message-ID: <8FA7FD0E-0754-4B92-BE51-33EFABB206F4@cs.cmu.edu>

https://cmu.zoom.us/j/96391712304?pwd=WGhzSy9kWnNpc3haZjd5bmVXV291QT09 <https://cmu.zoom.us/j/96391712304?pwd=WGhzSy9kWnNpc3haZjd5bmVXV291QT09>

We hope to see you there!

- Nick
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201203/7f791366/attachment.html>

From awd at cs.cmu.edu  Mon Dec  7 09:50:47 2020
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Mon, 7 Dec 2020 09:50:47 -0500
Subject: Fwd: MSR Thesis Talk: Learning Cyber-Physical Models of Resuscitation
In-Reply-To: <CAEJU0YoZnR6PqoqHd8ktDJSyKdxhHAap4aKPGwDaEy6sR=M=Kg@mail.gmail.com>
References: <CAEJU0YoZnR6PqoqHd8ktDJSyKdxhHAap4aKPGwDaEy6sR=M=Kg@mail.gmail.com>
Message-ID: <CAJvAoytaujPADhr1muoBWKSWKUeUvobi5PBKQVqG=GfakJhvpA@mail.gmail.com>

Team,

Mayra will be presenting her MSR work on Wednesday at noon.
Please join if available and if you are interested in cyber-physical models
and time series in critical care.

Cheers
Artur

---------- Forwarded message ---------
From: Mayra Melendez <mmelende at andrew.cmu.edu>
Date: Wed, Dec 2, 2020 at 4:28 PM
Subject: MSR Thesis Talk: Learning Cyber-Physical Models of Resuscitation
To: <ri-people at cs.cmu.edu>


Hello everyone,

I will be giving my MSR thesis talk on Wednesday, December 9th at 12:00 PM
EST via zoom.

*Date:* Wednesday, December 9th, 2020
*Time:* 12:00 PM - 1:00 PM EST
*Zoom link:*
https://cmu.zoom.us/j/2264817054?pwd=Nzlzb0lrZjVVZkhKZEhvTFlraXhXQT09
<https://www.google.com/url?q=https://cmu.zoom.us/j/2264817054?pwd%3DNzlzb0lrZjVVZkhKZEhvTFlraXhXQT09&sa=D&source=calendar&ust=1607376040681000&usg=AOvVaw3XMCi4SfNWvQ-K_6EA8p-5>
*Meeting ID:* 226 481 7054
*Password:* 268411

*Title:* Learning Cyber-Physical Models of Resuscitation

*Abstract: *
Ability to predict outcomes and forecast trajectories of recovery from
resuscitated intensive care patients could guide treatment decisions and
improve outcomes of care in both clinical and field settings. We develop a
machine learning driven cyber-physical model to provide such predictive
capabilities by leveraging arterial blood pressure (ABP) waveforms, one of
the routinely collected vital signs. A cohort of 51 Yorkshire pigs was
subjected to induced slow rate hemorrhage followed by fluid resuscitation.
To represent physics of the arterial system and emulate blood pressure
dynamics, we combine a two-element Windkessel model with an Unscented
Kalman Filter (UKF) to track the instantaneously estimated Windkessel
parameters over time. As the arterial pressure waveform exponentially
decays during diastole after each pump, we use UKF-tracked Windkessel
parameter estimates to identify time windows of ABP waveforms taken from
other subjects in the cohort to reconstruct the shapes of the test
subject?s ABP signal and its moving average. We allow UKF covariance to
temporarily increase to account for the effects of treatment such as
administering norepinephrine. When evaluated under leave-one-subject-out
cross-validation protocol, the model stays within 14+/-5% (mean+/-standard
deviation) of mean absolute percentage error when reconstructing the
current 250Hz ABP waveforms, and 19+/-6%, 24+/-6%, and 25+/-6% when
forecasting at 5, 15 and 30 minute horizons, respectively. Our results
demonstrate feasibility of using cyber-physical modeling of hemodynamic
waveform data to predict trajectories of resuscitation and therefore timely
inform treatment of hemorrhagic patients in both clinical and prolonged
field care settings.

*Committee:*
Artur Dubrawski (advisor)
Jeff Schneider
Nicholas Gisolfi

--
Mayra Melendez
MSR student, Robotics Institute - CMU
_______________________________________________
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/20201207/faee6742/attachment.html>

From predragp at andrew.cmu.edu  Tue Dec  8 23:57:25 2020
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Tue, 8 Dec 2020 23:57:25 -0500
Subject: CentOS is now dead!
Message-ID: <CAEFFt-F-EGGxccO1TfyHQ9N+4AU9K_ENGWvaEnjD36ixkWhRdQ@mail.gmail.com>

Dear Autonians,

CentOS is officially dead.

https://blog.centos.org/2020/12/future-is-centos-stream/#comments

IBM who aquired RedHat last year have pulled the plug on CentOS in similar
fashion Oracle did with OpenSolaris after SunMicrosystems aqusition. The
writing was on the wall ever since Red Hat killed Scientific Linux by
hiring off its developer from Fermi labs and shortly after hiring CentOS
project founders.

In the near term the above news will have no effect on the Auton Lab
computing infrastructure as we are using Springdale Linux, the oldest free
rebuilt of the RHEL by Princeton university. Long term RPM availability
might become problematic as people will have no incentive to create those
RPMs as free RHEL rebuilt ecosystem just shrunk 90%.

With Red Hat and SUSE Linux fully proprietary whithout stable community
edition, Ubuntu remains only other major relatively stable Linux distro
still available for free use.

I continue to monitor situation and reaction of major US national
laboratories who mostly use CentOS.

I wish I could tell you that this woul lead to major growth and popularity
of Springdale Linux or the raise of BSD based scientific computing
ecosystem but that seems very unlikely.

The newly minted PhDs should embrace themselves for the era of proprietary
OSs. Welcome back to 1980s,1990s and UNIX wars.

Cheers,
Predrag
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201208/0e8a56d1/attachment.html>

From predragp at andrew.cmu.edu  Wed Dec  9 10:05:44 2020
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Wed, 9 Dec 2020 10:05:44 -0500
Subject: CentOS is now dead!
In-Reply-To: <CAM+K4Xw5C6aJD4TN_td0Au+_ktx068WSyEnD=4+we2WuRW5gXQ@mail.gmail.com>
References: <CAEFFt-F-EGGxccO1TfyHQ9N+4AU9K_ENGWvaEnjD36ixkWhRdQ@mail.gmail.com>
 <CAM+K4Xw5C6aJD4TN_td0Au+_ktx068WSyEnD=4+we2WuRW5gXQ@mail.gmail.com>
Message-ID: <CAEFFt-HQwgcKaFFZHqmb6B-zHp-_NDn1zQ+gkef86rDtHt-owQ@mail.gmail.com>

Hi Robert,

FYI it is not the question of if but only when will Microsoft acquire
Canonical so Ubuntu might not live much longer either. The reasons why I
prefer to work with rebuilds of RHEL over Debian derivatives are of
technical nature, not the lack of familiarity. At the University of
Arizona, we were Debian/Ubunutu shop. That was my first exposure to Linux
after US research university started purging Irix first and then Solaris
from their computer labs in the late 90s. For me personally moving from
Solaris to Linux felt like the beginning of the decline. At this time most
national labs just like I do prefer to deal with RHEL clones. Desktops are
another story but all cool kids with money already use macOS even that Big
Sur sucks big time :-)

Springdale Linux is the oldest RHEL clone created by a dedicated team from
Princeton University, Institute for Advanced Studies, and Rutgers
supercomputing center. I don't see anything dramatically changing in the
near future.  Usually quiet Springdale Linux mailing list was buzzing with
activity this morning by mostly disfranchised CentOS users. It might be
short-lived but might actually strengthen our compunity.

Cheers,
Predrag



On Wed, Dec 9, 2020, 9:34 AM Robert Edman <redman at andrew.cmu.edu> wrote:

> fwiw, a few people (myself, Gus, Anthony) in the lab have been getting
> pretty good with running ubuntu in the lab environment. (I put it on my
> desktop when you said I should replace the OS, and I'm more familiar with
> administration of ubuntu than springdale - and in my experience, better
> package support). VPN, nfs, etc... are all up and running. If that is a
> direction you are forced to go in the future, we can at least give you some
> pointers.
>
> --Rob
>
> On Wed, Dec 9, 2020 at 1:23 AM Predrag Punosevac <predragp at andrew.cmu.edu>
> wrote:
>
>> Dear Autonians,
>>
>> CentOS is officially dead.
>>
>> https://blog.centos.org/2020/12/future-is-centos-stream/#comments
>>
>> IBM who aquired RedHat last year have pulled the plug on CentOS in
>> similar fashion Oracle did with OpenSolaris after SunMicrosystems
>> aqusition. The writing was on the wall ever since Red Hat killed Scientific
>> Linux by hiring off its developer from Fermi labs and shortly after hiring
>> CentOS project founders.
>>
>> In the near term the above news will have no effect on the Auton Lab
>> computing infrastructure as we are using Springdale Linux, the oldest free
>> rebuilt of the RHEL by Princeton university. Long term RPM availability
>> might become problematic as people will have no incentive to create those
>> RPMs as free RHEL rebuilt ecosystem just shrunk 90%.
>>
>> With Red Hat and SUSE Linux fully proprietary whithout stable community
>> edition, Ubuntu remains only other major relatively stable Linux distro
>> still available for free use.
>>
>> I continue to monitor situation and reaction of major US national
>> laboratories who mostly use CentOS.
>>
>> I wish I could tell you that this woul lead to major growth and
>> popularity of Springdale Linux or the raise of BSD based scientific
>> computing ecosystem but that seems very unlikely.
>>
>> The newly minted PhDs should embrace themselves for the era of
>> proprietary OSs. Welcome back to 1980s,1990s and UNIX wars.
>>
>> Cheers,
>> Predrag
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201209/56ba4a2b/attachment.html>

From gwelter at andrew.cmu.edu  Wed Dec  9 10:17:55 2020
From: gwelter at andrew.cmu.edu (Gus Welter)
Date: Wed, 9 Dec 2020 10:17:55 -0500
Subject: CentOS is now dead!
In-Reply-To: <CAEFFt-HQwgcKaFFZHqmb6B-zHp-_NDn1zQ+gkef86rDtHt-owQ@mail.gmail.com>
References: <CAEFFt-F-EGGxccO1TfyHQ9N+4AU9K_ENGWvaEnjD36ixkWhRdQ@mail.gmail.com>
 <CAM+K4Xw5C6aJD4TN_td0Au+_ktx068WSyEnD=4+we2WuRW5gXQ@mail.gmail.com>
 <CAEFFt-HQwgcKaFFZHqmb6B-zHp-_NDn1zQ+gkef86rDtHt-owQ@mail.gmail.com>
Message-ID: <CAACjBDXQDdYXG8WzjjRDUzOJa_HaiaZDZExb1yAcoqrEtRO3rw@mail.gmail.com>

Don't even say that about ms acquiring ubuntu, oh God....
And \agree about big sur sucks big time. Big step backward.

On Wed, Dec 9, 2020 at 10:06 AM Predrag Punosevac <predragp at andrew.cmu.edu>
wrote:

> Hi Robert,
>
> FYI it is not the question of if but only when will Microsoft acquire
> Canonical so Ubuntu might not live much longer either. The reasons why I
> prefer to work with rebuilds of RHEL over Debian derivatives are of
> technical nature, not the lack of familiarity. At the University of
> Arizona, we were Debian/Ubunutu shop. That was my first exposure to Linux
> after US research university started purging Irix first and then Solaris
> from their computer labs in the late 90s. For me personally moving from
> Solaris to Linux felt like the beginning of the decline. At this time most
> national labs just like I do prefer to deal with RHEL clones. Desktops are
> another story but all cool kids with money already use macOS even that Big
> Sur sucks big time :-)
>
> Springdale Linux is the oldest RHEL clone created by a dedicated team from
> Princeton University, Institute for Advanced Studies, and Rutgers
> supercomputing center. I don't see anything dramatically changing in the
> near future.  Usually quiet Springdale Linux mailing list was buzzing with
> activity this morning by mostly disfranchised CentOS users. It might be
> short-lived but might actually strengthen our compunity.
>
> Cheers,
> Predrag
>
>
>
> On Wed, Dec 9, 2020, 9:34 AM Robert Edman <redman at andrew.cmu.edu> wrote:
>
>> fwiw, a few people (myself, Gus, Anthony) in the lab have been getting
>> pretty good with running ubuntu in the lab environment. (I put it on my
>> desktop when you said I should replace the OS, and I'm more familiar with
>> administration of ubuntu than springdale - and in my experience, better
>> package support). VPN, nfs, etc... are all up and running. If that is a
>> direction you are forced to go in the future, we can at least give you some
>> pointers.
>>
>> --Rob
>>
>> On Wed, Dec 9, 2020 at 1:23 AM Predrag Punosevac <predragp at andrew.cmu.edu>
>> wrote:
>>
>>> Dear Autonians,
>>>
>>> CentOS is officially dead.
>>>
>>> https://blog.centos.org/2020/12/future-is-centos-stream/#comments
>>>
>>> IBM who aquired RedHat last year have pulled the plug on CentOS in
>>> similar fashion Oracle did with OpenSolaris after SunMicrosystems
>>> aqusition. The writing was on the wall ever since Red Hat killed Scientific
>>> Linux by hiring off its developer from Fermi labs and shortly after hiring
>>> CentOS project founders.
>>>
>>> In the near term the above news will have no effect on the Auton Lab
>>> computing infrastructure as we are using Springdale Linux, the oldest free
>>> rebuilt of the RHEL by Princeton university. Long term RPM availability
>>> might become problematic as people will have no incentive to create those
>>> RPMs as free RHEL rebuilt ecosystem just shrunk 90%.
>>>
>>> With Red Hat and SUSE Linux fully proprietary whithout stable community
>>> edition, Ubuntu remains only other major relatively stable Linux distro
>>> still available for free use.
>>>
>>> I continue to monitor situation and reaction of major US national
>>> laboratories who mostly use CentOS.
>>>
>>> I wish I could tell you that this woul lead to major growth and
>>> popularity of Springdale Linux or the raise of BSD based scientific
>>> computing ecosystem but that seems very unlikely.
>>>
>>> The newly minted PhDs should embrace themselves for the era of
>>> proprietary OSs. Welcome back to 1980s,1990s and UNIX wars.
>>>
>>> Cheers,
>>> Predrag
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201209/347547c2/attachment-0001.html>

From ngisolfi at cs.cmu.edu  Thu Dec 10 11:28:12 2020
From: ngisolfi at cs.cmu.edu (Nick Gisolfi)
Date: Thu, 10 Dec 2020 11:28:12 -0500
Subject: [Lunch] Today @noon over Zoom
Message-ID: <36FF09CD-869F-40D1-BFE4-17965C454304@cs.cmu.edu>

https://cmu.zoom.us/j/96391712304?pwd=WGhzSy9kWnNpc3haZjd5bmVXV291QT09 <https://cmu.zoom.us/j/96391712304?pwd=WGhzSy9kWnNpc3haZjd5bmVXV291QT09>

We hope to see you there!

- Nick
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201210/035fa8d8/attachment.html>

From predragp at andrew.cmu.edu  Fri Dec 11 23:31:10 2020
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Fri, 11 Dec 2020 23:31:10 -0500
Subject: lov10,lov11,lov12,lov13 provisioned
Message-ID: <CAEFFt-EcDA=h6gzh8UeL9ih++Wu+9-p-D0PtxvdMRD9zY8YX-w@mail.gmail.com>

Dear Autonians,

Four new CPU nodes we received in late September are finally provisioned.
Each one is 88 cores and 768 GB of RAM. I am adding scratch directories
right now but the nodes are should be usable. Let me know if notice
anything strange. The provisioning process is semi-automatic. For the most
part, I just run Ansible playbooks and intervene only to fix corner cases.
Hopefully,  one of these days I will fix my Ansible JSON files so that no
human intervention is needed.

Auton cluster is now in pretty decent shape and well organized in five
server racks. Two of those are not filled to full capacity and I can
provision new CPU or GPU nodes on short notice (in one day under no Covid
restriction).

I will try to fix LOW1 but only after I do a bit of work on file servers. I
have over 600 TB of HDDs laying around and it will take me a while to
populate all available driver bays and replace old HDDs.

Cheers,
Predrag
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201211/230b8ba6/attachment.html>

From predragp at andrew.cmu.edu  Sat Dec 12 00:21:26 2020
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Sat, 12 Dec 2020 00:21:26 -0500
Subject: lov[7-9] scratch space to be expanded
Message-ID: <CAEFFt-EFzatXZOqq+LhE-PmSwFg5XJMKTaA7idw3x2NcMOYP3A@mail.gmail.com>

Dear Autonians,

While I was in the server room I added HDDs to lov7, lov8, lov9 machines. I
would like to nuke the current miniscule /home/scratch and replace it with
2TB partition. If you have something on it please remove it by 9:00 PM
Saturday 12th of December or ping me if you need more time.

Cheers,
Predrag
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201212/4ab1b053/attachment.html>

From awd at cs.cmu.edu  Sat Dec 12 07:54:14 2020
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Sat, 12 Dec 2020 07:54:14 -0500
Subject: lov10,lov11,lov12,lov13 provisioned
In-Reply-To: <CAEFFt-EcDA=h6gzh8UeL9ih++Wu+9-p-D0PtxvdMRD9zY8YX-w@mail.gmail.com>
References: <CAEFFt-EcDA=h6gzh8UeL9ih++Wu+9-p-D0PtxvdMRD9zY8YX-w@mail.gmail.com>
Message-ID: <CAJvAoytgT3MYKdD1M2CyFhiLjRdsrc0W3tg95O+JHzepz8u52Q@mail.gmail.com>

Thanks very much Predrag.

Everyone in the Lab greatly appreciates your dedication to keep the
substantial hardware and software we own operational in spite of the
difficulties caused by the pandemic.

Cheers!
Artur

On Fri, Dec 11, 2020 at 11:31 PM Predrag Punosevac <predragp at andrew.cmu.edu>
wrote:

> Dear Autonians,
>
> Four new CPU nodes we received in late September are finally provisioned.
> Each one is 88 cores and 768 GB of RAM. I am adding scratch directories
> right now but the nodes are should be usable. Let me know if notice
> anything strange. The provisioning process is semi-automatic. For the most
> part, I just run Ansible playbooks and intervene only to fix corner cases.
> Hopefully,  one of these days I will fix my Ansible JSON files so that no
> human intervention is needed.
>
> Auton cluster is now in pretty decent shape and well organized in five
> server racks. Two of those are not filled to full capacity and I can
> provision new CPU or GPU nodes on short notice (in one day under no Covid
> restriction).
>
> I will try to fix LOW1 but only after I do a bit of work on file servers.
> I have over 600 TB of HDDs laying around and it will take me a while to
> populate all available driver bays and replace old HDDs.
>
> Cheers,
> Predrag
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201212/9ebdf875/attachment.html>

From awd at cs.cmu.edu  Sat Dec 12 08:28:52 2020
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Sat, 12 Dec 2020 08:28:52 -0500
Subject: Emily Kennedy - Outstanding CMU Alumna
Message-ID: <CAJvAoyvEuKAhX1cafKyDmvn=Z-P_S1Kh44wQycaM478=gNDc9Q@mail.gmail.com>

Dear Autonians,

Please join me in congratulating our own Emily Kennedy for a very well
deserved recognition!

She - and other recipients of the CMU Alumni Awards - will be celebrated at
an open event on Wednesday, December 16. Here is the link (you need to
register, but it's free):
https://cmucommunity.force.com/customquickevents?id=a3p2S000000DxYP&custom=true&cd=1

And the text of the announcement of Emily's recognition can be found below.

Congrats Emily!
Artur

The Outstanding Recent Alumna Award is given for exemplary professional or
vocational success and/or service to the university in the first decade as
graduate. The 2020 honoree is:

Emily Kennedy, a 2012 graduate of the Dietrich College of Humanities and
Social Sciences, is fighting human trafficking with artificial intelligence
technology. She founded Marinus Analytics to gather intelligence and
identify victims for the FBI and National Center for Missing & Exploited
Children and hosts ?The Empower Podcast? to create a dialogue on issues
important to women.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201212/5da70291/attachment-0001.html>

From predragp at andrew.cmu.edu  Sun Dec 13 00:36:19 2020
From: predragp at andrew.cmu.edu (Predrag Punosevac)
Date: Sun, 13 Dec 2020 00:36:19 -0500
Subject: lov[7-9] scratch space to be expanded
In-Reply-To: <CAEFFt-EFzatXZOqq+LhE-PmSwFg5XJMKTaA7idw3x2NcMOYP3A@mail.gmail.com>
References: <CAEFFt-EFzatXZOqq+LhE-PmSwFg5XJMKTaA7idw3x2NcMOYP3A@mail.gmail.com>
Message-ID: <CAEFFt-GVWbcuD4V6JJtHdQ=NbKu9u1y4C_8DxtEYZMnRtiko9A@mail.gmail.com>

The scratch space is now added to lov[7-9]. These three machines are
updated to 8.3 including /opt/minconda3 to python 3.8.5

On a related note, I did a quick update (including conda) and inspection of
the CPU computing nodes still running Springdale 7.9 (RHEL 7.9). lov[1-6],
Ari, Foxconn, Athena (9 in total excluding defunct low1). All of those
machines have adequate scratch spaces (mostly 2 TB with additional RAID 10
TB storage available on a few of them). Non the less scratch appears to be
nearly full which limits usability. I would hate to wield my root access to
get things under control. Please be mindful of your fellow Lab scientists.

In case you wonder EOL for Springdale 7.9 is 2024 but it would be good to
upgrade at least newer machines to branch 8.xxx for a number of reasons.
That would have to wait until I have unrestricted access to the server
room. Springdale is here to stay and it finally got some attention due to
the ill-fated CentOS.

https://arstechnica.com/gadgets/2020/12/centos-linux-is-gone-but-its-refugees-have-alternatives/

In a case, you wonder a CMU guy with ten years of experience using
Springdale is yours truly.

Cheers,
Predrag

P.S. I was not touching GPU nodes at this time due to the fragility of
NVidia binary blob drivers and "deep" learning ecosystem. In my
experience NVidia driver will eventually get broken and then I will refresh
those machines. 14 out of 23 machines run older RHEL 7.9 clone. Those
should be eventually upgraded. We do have two other GPU nodes that run
Ubuntu 16.04. They are generally off-limit for most lab users. I have no
immediate plans to do any work on them.





On Sat, Dec 12, 2020 at 12:21 AM Predrag Punosevac <predragp at andrew.cmu.edu>
wrote:

> Dear Autonians,
>
> While I was in the server room I added HDDs to lov7, lov8, lov9 machines.
> I would like to nuke the current miniscule /home/scratch and replace it
> with 2TB partition. If you have something on it please remove it by 9:00 PM
> Saturday 12th of December or ping me if you need more time.
>
> Cheers,
> Predrag
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201213/95452701/attachment.html>

From awd at cs.cmu.edu  Thu Dec 17 17:15:47 2020
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Thu, 17 Dec 2020 17:15:47 -0500
Subject: Fwd: [ML-news] [CFP REMINDER] ACM-CHIL 2021 - Conference on Health,
 Inference and Learning (Virtual, April 2021)
In-Reply-To: <b1895df8-da5b-47fd-b986-67470d690cebn@googlegroups.com>
References: <b1895df8-da5b-47fd-b986-67470d690cebn@googlegroups.com>
Message-ID: <CAJvAoysrh8h3xE1cmmQX=sZEt34spCSo4NGzKiDt27s5wNUNTA@mail.gmail.com>

fyi, in particular if you're working in applications to healthcare

---------- Forwarded message ---------
From: Stephanie Hyland <steph.hyland at gmail.com>
Date: Thu, Dec 17, 2020 at 4:20 PM
Subject: [ML-news] [CFP REMINDER] ACM-CHIL 2021 - Conference on Health,
Inference and Learning (Virtual, April 2021)
To: Machine Learning News <ml-news at googlegroups.com>


The ACM Conference on Health, Inference, and Learning (ACM-CHIL 2021)
solicits work across a variety of disciplines, including machine learning,
statistics, epidemiology, health policy, operations, and economics.
ACM-CHIL 2021 invites submissions touching on topics focused on relevant
problems affecting health. Authors are invited to submit 8-10 page papers
(with unlimited pages for references) to each of the tracks described below.

Link to CFP: https://www.chilconference.org/call-for-papers.html

*Important Dates*

   - Abstracts due ? January 7, 2021 (11:59 pm AoE)
   - Submissions due ? January 11, 2021 (11:59 pm AoE)
   - Notification of Acceptance ? Feb 15, 2021 (11:59 pm AoE)
   - Camera Ready Due ? March 5, 2021 (11:59 pm AoE)
   - Conference Dates ? April 8-10, 2021 (to be held virtually)

*=== Tracks and topics ===*

   - Track 1: Models and Methods
   - Track 2: Applications and Practice
   - Track 3: Impact and Society

Topics for each track include but are not restricted to:

*Track 1 (Models and Methods):*

   - (Un)supervised learning, representation learning
   - Natural language processing, knowledge graphs
   - Computer vision
   - Survival analysis
   - Deep learning architectures
   - Transfer learning, domain adaptation
   - Bayesian learning, inference
   - Structured learning
   - Robust learning
   - Causal inference


*Track 2 (Applications and Practice):*

   - Examination of robustness of ML systems to real-world dataset shift,
   adversarial shift, or on minority subpopulations
   - Investigations into model performance on minority subpopulations, and
   the implications thereof
   - Scalable, safe machine learning/inference in clinical environments
   - New tools or comprehensive benchmarks for machine learning for
   healthcare
   - Development of scalable systems for processing data in practice
   (demonstrating, e.g., concern for multi-modality, runtime, robustness,
   etc., as guided by a clinical use case)
   - Bridging the deployment gap
   - Remote, wearable, and telehealth
   - Data or software packages


*Track 3 (Impact and Society):*


   - Fairness, equity, ethics and justice
   - Model implementation, deployment, and adoption
   - Policy, public health, and societal impact of algorithms
   - Interpretability
   - System design for implementation of ML at scale
   - Regulatory frameworks
   - Tools for adoption of ML
   - Evaluation of bias in legal and/or health contexts
   - Human-algorithm interaction


For more detail on the scope of each track, consult the online CFP:
https://www.chilconference.org/call-for-papers.html

In case you are not sure which track your submission fits under, feel free
to contact the track or program committee chairs for clarification.

*=== Submission Details and Guidelines ===*

For full details, refer to the online CFP:
https://www.chilconference.org/call-for-papers.html

*Length and Formatting*
Submitted papers must be 8-10 pages (including all figures and tables),
plus unlimited pages for references. Additional supplementary materials
(e.g., appendices) can be submitted with their main manuscript. Reviewers
will not be required to read the supplementary materials. Papers that are
neither in ACM format or exceeding the specified page length, may be
rejected without review.

*Archival Submissions*
Submissions to the main conference are considered archival and will appear
in the published proceedings of the conference if accepted.

*Dual Submission Policy*
You may not submit papers that are identical, or substantially similar to
versions that are currently under review at another conference or journal,
have been previously published, or have been accepted for publication.
Submissions to the main conference are considered archival and will appear
in the published proceedings of the conference if accepted.

An exception to this rule is extensions of workshop papers that have
previously appeared in non-archival venues, such as workshops, arXiv, or
similar without formal proceedings. These works may be submitted as-is or
in an extended form. ACM-CHIL also welcomes full paper submissions that
extend previously published short papers or abstracts, so long as the
previously published version does not exceed 4 pages in length. Note that
the submission should not cite the workshop/report and preserve anonymity
in the submitted manuscript.


*Peer Review*
The review process is double-blind. Please submit completely anonymized
drafts. Please do not include any identifying information, and refrain from
citing the authors? own prior work in anything other than third-person.
Violations to this policy may result in rejection without review.

Conference organizers and reviewers are required to maintain
confidentiality of submitted material. Upon acceptance, the titles,
authorship, and abstracts of papers will be released prior to the
conference.

*Open Access*
ACM-CHIL is committed to open science and ensuring our proceedings are
freely available. The conference will make use of the ?ACM Authorizer ?Open
Access? Service? and ?ACM OpenTOC Service?, allowing unrestricted access to
individual papers as well as the overall proceedings.


*=== ACM-CHIL 2021 Organisers ===*
Dr. Marzyeh Ghassemi, Dr. Tristan Naumann, Dr. Emma Pierson, Emily
Alsentzer, Matthew McDermott, Dr. George Chen, Dr. Stephanie Hyland, Dr.
Sanja ??epanovi?, Dr. Sanmi Koyejo, Dr. Joyce Ho, Dr. Brett Beaulieu-Jones,
Irene Chen, Dr. Jessica Gronsbell, Dr. Tom Pollard

Track 1 Chairs: Dr. Michael Hughes, Dr. Shalmali Joshi, Dr. Rajesh
Ranganath, Dr. Rahul G. Krishnan
Track 2 Chairs: Dr. Tom Pollard, Dr. Bobak Mortazavi, Dr. Andrew Beam, Dr.
Uri Shalit
Track 3 Chairs: Dr. Alistair Johnston, Dr. Rumi Chunara, Dr. George Chen

-- 
You received this message because you are subscribed to the Google Groups
"Machine Learning News" group.
To unsubscribe from this group and stop receiving emails from it, send an
email to ml-news+unsubscribe at googlegroups.com.
To view this discussion on the web visit
https://groups.google.com/d/msgid/ml-news/b1895df8-da5b-47fd-b986-67470d690cebn%40googlegroups.com
<https://groups.google.com/d/msgid/ml-news/b1895df8-da5b-47fd-b986-67470d690cebn%40googlegroups.com?utm_medium=email&utm_source=footer>
.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20201217/11bf5959/attachment.html>