From pbartosi at andrew.cmu.edu  Wed Nov  1 12:48:04 2023
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Wed, 1 Nov 2023 12:48:04 -0400
Subject: GPU12 maintenance
In-Reply-To: <CAGAXpPcp-atyp=Ohnm4j44HSkMw6xOCvmKmbsX3ODBHD-VC5HA@mail.gmail.com>
References: <CAN_-bZJO3a3KdX=JHO-xEY0CZ1-7Kdn9cPnOyCULGoSfCrEPeA@mail.gmail.com>
 <CAGAXpPcXs339mMarz+wLht2c0Ge1oKt7_Mc5Oode7sap8VmAsA@mail.gmail.com>
 <CAN_-bZLdUNAdjMN0exX=L+6KYs6uWTSpS15Pqa+mgi=ewFQ8zw@mail.gmail.com>
 <CAGAXpPcp-atyp=Ohnm4j44HSkMw6xOCvmKmbsX3ODBHD-VC5HA@mail.gmail.com>
Message-ID: <CAN_-bZJV+iQytHbQ_oJxraQ2yRBMSS=FrcGi0Rr-_=2Sx6GnZw@mail.gmail.com>

GPU12 is up and running.

OS: Springdale 9.2
glibc 2.34
CUDA: 11.8 (nvcc)
python 3.9

Piotr.


On Thu, Oct 26, 2023 at 2:26?PM Chang Liu <changl8 at andrew.cmu.edu> wrote:

> Thank you! I'll wait for a while :)
>
> On Fri, Oct 27, 2023 at 2:24?AM Piotr Bartosiewicz <
> pbartosi at andrew.cmu.edu> wrote:
>
>> Might be Predrag patching network devices. Just wait.
>>
>> Piotr.
>>
>>
>> On Thu, Oct 26, 2023 at 2:19?PM Chang Liu <changl8 at andrew.cmu.edu> wrote:
>>
>>> Hi Piotr,
>>>
>>> Is there any maintenance on the cluster just now? can't seem to connect
>>> to any of them.
>>>
>>> Thanks,
>>> Chang
>>>
>>> On Fri, Oct 27, 2023 at 1:37?AM Piotr Bartosiewicz <
>>> pbartosi at andrew.cmu.edu> wrote:
>>>
>>>> GPU12 will be taken down for maintenance.
>>>>
>>>> Start date: Monday 10/29/2023
>>>> Duration: approx 2 days
>>>> Purpose: system upgrade
>>>>
>>>> Please do not start any new tasks and save all the work you are running
>>>> on the named machine.
>>>>
>>>> Thank you for your attention,
>>>> Piotr.
>>>>
>>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231101/62d441df/attachment.html>

From pbartosi at andrew.cmu.edu  Wed Nov  1 12:54:45 2023
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Wed, 1 Nov 2023 12:54:45 -0400
Subject: GPU11 maintenance
Message-ID: <CAN_-bZJS0wd9oPUbpPphCtmJaWbCDiWORdKeYZXYjLqdGz5aTQ@mail.gmail.com>

GPU11 will be taken down for maintenance.

Start date: Monday 11/06/2023
Duration: approx 2 days
Purpose: system upgrade

Please do not start any new tasks and save all the work you are running on
the named machine.

Thank you,
Piotr.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231101/abc7c139/attachment.html>

From awd at cs.cmu.edu  Thu Nov  2 11:44:10 2023
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Thu, 2 Nov 2023 11:44:10 -0400
Subject: Fwd: RI Ph.D. Thesis Proposal: Jack Good
In-Reply-To: <CAPfXyx+3E5B+_ujyJRvpx6g33WHSOZXdhkr18CHRpN_G+S+aTg@mail.gmail.com>
References: <CAPfXyx+3E5B+_ujyJRvpx6g33WHSOZXdhkr18CHRpN_G+S+aTg@mail.gmail.com>
Message-ID: <CAJvAoyuWvh8LTncUqHsNdsYOf_DFnWNQL0_aW8Gxx7DzME7yuQ@mail.gmail.com>

Please mark your calendars and plan to attend a very amusing presentation
by Jack!

Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Thu, Nov 2, 2023 at 11:42?AM
Subject: RI Ph.D. Thesis Proposal: Jack Good
To: RI People <ri-people at andrew.cmu.edu>


Date: 14 November 2023
Time: 4:30 p.m. (ET)
Location: GHC 8102

Zoom Link:
https://cmu.zoom.us/j/96881722005?pwd=NjhCb2gwQ3ZzSmtlVlJ3Qnp5QTd1Zz09

Type: Ph.D. Thesis Proposal
Who: Jack Good
Title: Trustworthy Learning using Uncertain Interpretation of Data



Abstract:

Non-parametric models are popular in real-world applications of machine
learning. However, many modern ML methods that ensure that models are
pragmatic, safe, robust, fair, and otherwise trustworthy in increasingly
critical applications, assume parametric, differentiable models. We show
that, by interpreting data as locally uncertain, we can achieve many of
these without being limited to parametric or inherently differentiable
models. In particular, we focus on decision trees, which are popular for
their good performance on tabular data as well as ease of use, low design
cost, low computational requirements, fast inference, and interpretability.
We propose a new kind of fuzzy decision tree we call a kernel density
decision tree (KDDT) because the uncertain input interpretation is similar
to kernel density estimation.

We organize the completed and proposed contributions of this thesis into
three pillars. The first pillar is robustness and verification: we show
improvement of robustness to various adverse conditions and discuss
verification of safety properties for FDTs and KDDTs. The second pillar is
interpretability: by leveraging the efficient fitting and differentiability
of our trees, we alternatingly optimize a parametric feature transformation
using gradient descent and the tree by refitting to obtain compact,
interpretable single-tree models with competitive performance. The third
pillar is pragmatic advancements: we make advances in semi-supervised
learning, federated learning, and ensemble merging for decision trees.



Thesis Committee Members:

Artur Dubrawski, Chair

Jeff Schneider

Tom Mitchell

Gilles Clermont, University of Pittsburgh
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231102/96408657/attachment.html>

From pbartosi at andrew.cmu.edu  Tue Nov  7 11:17:46 2023
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Tue, 7 Nov 2023 11:17:46 -0500
Subject: GPU11 maintenance
In-Reply-To: <CAN_-bZJS0wd9oPUbpPphCtmJaWbCDiWORdKeYZXYjLqdGz5aTQ@mail.gmail.com>
References: <CAN_-bZJS0wd9oPUbpPphCtmJaWbCDiWORdKeYZXYjLqdGz5aTQ@mail.gmail.com>
Message-ID: <CAN_-bZL-D1ORDbf9KxE9MK9tXdr_H1p1iqCckcL7K+27ivRawg@mail.gmail.com>

GPU11 is up and running.

OS: Springdale 9.2
glibc 2.34
CUDA: 11.8 (nvcc)
python 3.9

Piotr.


On Wed, Nov 1, 2023 at 12:54?PM Piotr Bartosiewicz <pbartosi at andrew.cmu.edu>
wrote:

> GPU11 will be taken down for maintenance.
>
> Start date: Monday 11/06/2023
> Duration: approx 2 days
> Purpose: system upgrade
>
> Please do not start any new tasks and save all the work you are running on
> the named machine.
>
> Thank you,
> Piotr.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231107/0b4180ba/attachment.html>

From awd at cs.cmu.edu  Sat Nov 11 18:39:08 2023
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Sat, 11 Nov 2023 18:39:08 -0500
Subject: Tuesday 430pm at GHC 8102: RI Ph.D. Thesis Proposal: Jack Good
In-Reply-To: <CAPfXyx+3E5B+_ujyJRvpx6g33WHSOZXdhkr18CHRpN_G+S+aTg@mail.gmail.com>
References: <CAPfXyx+3E5B+_ujyJRvpx6g33WHSOZXdhkr18CHRpN_G+S+aTg@mail.gmail.com>
Message-ID: <CAJvAoysxEzRdGQJiOLB-hHSGay8ctayJPNSpv1cBUiJty=ptdg@mail.gmail.com>

A reminder about this exciting event!

See yinz there.

Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Thu, Nov 2, 2023 at 11:42?AM
Subject: RI Ph.D. Thesis Proposal: Jack Good
To: RI People <ri-people at andrew.cmu.edu>


Date: 14 November 2023
Time: 4:30 p.m. (ET)
Location: GHC 8102

Zoom Link:
https://cmu.zoom.us/j/96881722005?pwd=NjhCb2gwQ3ZzSmtlVlJ3Qnp5QTd1Zz09

Type: Ph.D. Thesis Proposal
Who: Jack Good
Title: Trustworthy Learning using Uncertain Interpretation of Data



Abstract:

Non-parametric models are popular in real-world applications of machine
learning. However, many modern ML methods that ensure that models are
pragmatic, safe, robust, fair, and otherwise trustworthy in increasingly
critical applications, assume parametric, differentiable models. We show
that, by interpreting data as locally uncertain, we can achieve many of
these without being limited to parametric or inherently differentiable
models. In particular, we focus on decision trees, which are popular for
their good performance on tabular data as well as ease of use, low design
cost, low computational requirements, fast inference, and interpretability.
We propose a new kind of fuzzy decision tree we call a kernel density
decision tree (KDDT) because the uncertain input interpretation is similar
to kernel density estimation.

We organize the completed and proposed contributions of this thesis into
three pillars. The first pillar is robustness and verification: we show
improvement of robustness to various adverse conditions and discuss
verification of safety properties for FDTs and KDDTs. The second pillar is
interpretability: by leveraging the efficient fitting and differentiability
of our trees, we alternatingly optimize a parametric feature transformation
using gradient descent and the tree by refitting to obtain compact,
interpretable single-tree models with competitive performance. The third
pillar is pragmatic advancements: we make advances in semi-supervised
learning, federated learning, and ensemble merging for decision trees.



Thesis Committee Members:

Artur Dubrawski, Chair

Jeff Schneider

Tom Mitchell

Gilles Clermont, University of Pittsburgh
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231111/ed68d237/attachment.html>

From mgoswami at andrew.cmu.edu  Mon Nov 13 11:44:38 2023
From: mgoswami at andrew.cmu.edu (Mononito Goswami)
Date: Mon, 13 Nov 2023 11:44:38 -0500
Subject: GPU 28 has no scratch space left
Message-ID: <CAM5bA72wrJahN1kpswTJQwvU4UaCbwUQQ8jZSoNDes7Cbn+TVA@mail.gmail.com>

Hi all,
There is almost no scratch space left on GPU 28, rendering it partially
unusable. Please remove your data after your experiments are over.

Filesystem      Size  Used Avail Use% Mounted on
/dev/nvme0n1    894G  891G  3.2G 100% /home/scratch

--
As a reminder:
You can use
$ df -h /home/scratch/
to check the available disk space.

And
$ du -h --max-depth=1 /home/scratch/myusername/
to check how much space your files and folders in your directory take up.

Best,
Mononito
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231113/08db34a2/attachment.html>

From vmundhed at andrew.cmu.edu  Tue Nov 21 00:34:41 2023
From: vmundhed at andrew.cmu.edu (Vedant Mundheda)
Date: Tue, 21 Nov 2023 00:34:41 -0500
Subject: GPU 15 No scratch space left
Message-ID: <CAGhe7JR3JcMU5Hbnq1fN0UtjUKP9CwZZL=1Yy=vOBGMA2sgBGA@mail.gmail.com>

Hi all,

There is no scratch space remaining on GPU15. Could you please remove the
data after the experiments are completed.

Thank you,
Vedant Mundheda
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231121/7fa9503b/attachment.html>

From xintongd at andrew.cmu.edu  Wed Nov 22 11:54:49 2023
From: xintongd at andrew.cmu.edu (Xintong Duan)
Date: Wed, 22 Nov 2023 11:54:49 -0500
Subject: GPU 27 has no scratch space left
Message-ID: <CABPmb-FJc8EV7YtP7Td0ZbsC=XAPi-VQmA-9Vap6wZEose2nhw@mail.gmail.com>

Hi all,

There is no scratch space left on gpu27. Could you please remove the data
if your experiment is over? Thanks.

Best,
Xintong
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231122/12720743/attachment.html>

From mike.wirtz89 at proton.me  Thu Nov 23 13:17:50 2023
From: mike.wirtz89 at proton.me (Mike Wirtz)
Date: Thu, 23 Nov 2023 18:17:50 +0000
Subject: Ecommerce Expertise
Message-ID: <U4hhv9uXMvnoJbShWj51PsyIRY_Gtqg0oORs_GeT8VwbYjMUyiWtLF6QY_pKWA7UhBqvHaMBKzYMFjl0iCrQ0DcpYrE-aP4wslpnJqAh_eI=@proton.me>

As we look towards the future, <strong>ecommerce</strong> continues to evolve at an unprecedented pace, driven by technological advancements and changing consumer behaviors. The integration of AI, AR, and personalized shopping experiences are not just trends, but essential components for the success of online businesses. A key player in understanding and navigating these changes is <a href="https://himanuel.com">ecommerce expertise</a> offered by himanuel.com, a website recognized for its rich experience and in-depth insights into the ecommerce space. Their expertise sheds light on innovative strategies and forward-thinking approaches that are shaping the future of online retail.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231123/09f7746f/attachment.html>

From avillaflor at cmu.edu  Thu Nov 23 19:19:32 2023
From: avillaflor at cmu.edu (Adam Villaflor)
Date: Thu, 23 Nov 2023 16:19:32 -0800
Subject: GPU 26 is out of scratch space
Message-ID: <CAGW4Btz3W7QKScL8eywFa_VPMeevbLsYShXcptD5q4pbuTA46g@mail.gmail.com>

Hi everyone,

GPU26 is out of scratch space. If you have unused data on gpu26, could you
please clear it when possible.

Happy holidays!

Best,
Adam
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20231123/7459efc4/attachment.html>