From pbartosi at andrew.cmu.edu  Thu Jan  2 11:03:16 2025
From: pbartosi at andrew.cmu.edu (Piotr Bartosiewicz)
Date: Thu, 2 Jan 2025 11:03:16 -0500
Subject: Machine Room Power Outage 1//7/25
Message-ID: <CAN_-bZ+2ERvPp4hUfy53XJbzB-0jZcUm3Nj4XQE8tP9Rxw2vsg@mail.gmail.com>

Hi,
  there will be a power outage in the machine room on 1/7/25.
Our machines will be unavailable during this time.

Estimated time: 7am - 11am

We need to power down our servers earlier so please save your work no later
than the evening of 1/6/25.

Piotr.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250102/6d6ee228/attachment.html>

From jeff4 at andrew.cmu.edu  Fri Jan 17 13:01:44 2025
From: jeff4 at andrew.cmu.edu (Jeff Schneider)
Date: Fri, 17 Jan 2025 13:01:44 -0500
Subject: Fwd: Reminder - Thesis Defense - January 17, 2025 - Arundhati
 Banerjee - Learning based approaches to practical challenges in multi-agent
 active search
In-Reply-To: <7196c07f-39d5-48ba-a3e6-1ef81ace8bd6@andrew.cmu.edu>
References: <7196c07f-39d5-48ba-a3e6-1ef81ace8bd6@andrew.cmu.edu>
Message-ID: <3f07bf09-9622-475b-a4a1-be0b1d6f74bb@andrew.cmu.edu>

reminder: Please come and see Arundhati's thesis defense happening now



-------- Forwarded Message --------
Subject: 	Reminder - Thesis Defense - January 17, 2025 - Arundhati 
Banerjee - Learning based approaches to practical challenges in 
multi-agent active search
Date: 	Fri, 17 Jan 2025 12:23:22 -0500
From: 	Diane L Stidle <stidle at andrew.cmu.edu>
To: 	ml-seminar at cs.cmu.edu <ML-SEMINAR at CS.CMU.EDU>, yyue at caltech.edu



*/Thesis Defense/*

Date: January 17, 2025
Time: 1:00pm (EST)
Place: GHC 4405 & Remote
PhD Candidate: Arundhati Banerjee

*Title: Learning based approaches to practical challenges in multi-agent 
active search*

Abstract:
Interactive decision making is essential for the functioning of 
autonomous agents in both software and embodied applications. Typically, 
agents interact in a multi-agent environment with the goal of fulfilling 
individual or shared objectives. In this thesis, we study the 
multi-agent adaptive decision making problem in the framework of 
Multi-Agent Active Search (MAAS) with a focus on applications like 
search and rescue, wildlife patrolling or environment monitoring with 
multi-robot teams.

Multi-Agent active search?involves a team of robots (agents) deciding 
/when /and /where/ to gather information about their surroundings, 
conditioned on their past observations, in order to estimate the 
presence and position of different objects of interest (OOIs) or 
targets.?Agents communicate with each other asynchronously, without 
relying on a central controller to coordinate the agents' 
interactions.?Realistically, inter-agent communications may be 
unreliable, and robots in the wild have to deal with noisy observations 
and stochastic environment dynamics.?Our setup formalizes MAAS with 
practical models of real-world sensing, noise, and communication 
constraints for aerial and ground robots.

Part I of this thesis studies the benefits of non-myopic lookahead 
decision making in MAAS with Thompson sampling and Monte Carlo Tree 
Search.?Additionally, we consider a multi-objective pareto-optimization 
setup for cost-aware active search, highlighting the challenges due to 
partial observability, decentralized multi-agent decision making, and 
computational complexity with combinatorial action search spaces.?In 
Part II, we focus on the practical challenges due to observation noise 
and dynamic targets in multi-agent active search and tracking.?Our 
proposed algorithms using Bayesian filtering in these settings 
empirically demonstrate the importance of uncertainty modeling for 
inference and decision making with noisy observations due to sensor 
errors or environment non-stationarity. Part III?shifts focus to 
generative models for decision making, particularly the applicability of 
diffusion for lookahead MAAS with observation noise.?In the final part, 
we discuss the broader applicability of these methods in the context of 
multi-agent decision making in robotics and other applications with 
similar real world constraints.

*Thesis Committee*:
Jeff Schneider (Chair)
Geoff Gordon
Barnab?s P?czos
Yisong Yue (Caltech)

Link to the draft document:
https://drive.google.com/drive/folders/1YsZgROFeltk4TUVYo-9ldoSlsEkTjaAB?usp=sharing

Zoom meeting link:
https://cmu.zoom.us/j/2231085641?pwd=j7ZOUGOHWPnaCe6c2FuCW3Xb0q8cWb.1&omn=99132356799 
<https://cmu.zoom.us/j/2231085641?pwd=j7ZOUGOHWPnaCe6c2FuCW3Xb0q8cWb.1&omn=99132356799>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250117/d26a3735/attachment.html>

From awd at cs.cmu.edu  Tue Jan 21 09:45:32 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Tue, 21 Jan 2025 09:45:32 -0500
Subject: Fwd: [ML-news] Announcing the PhysioNet Challenge 2025
In-Reply-To: <b1942219-7087-4153-b00c-d36f97173fddn@googlegroups.com>
References: <b1942219-7087-4153-b00c-d36f97173fddn@googlegroups.com>
Message-ID: <CAJvAoyu4MCa86ryAU=f7ERXSEmXPEpux-eO80YxZs70WOuQwAQ@mail.gmail.com>

Fyi, very relevant to all of us who work on algorithms for time series
analysis, especially foundation models

A.

---------- Forwarded message ---------
From: gari.c... at gmail.com <gari.clifford at gmail.com>
Date: Tue, Jan 21, 2025, 9:27?AM
Subject: [ML-news] Announcing the PhysioNet Challenge 2025
To: Machine Learning News <ml-news at googlegroups.com>


*Announcing the PhysioNet Challenge 2025*



Dear Community,



We are excited to announce the opening of the George B. Moody PhysioNet
Challenge 2025 <https://physionetchallenges.org/2025/>. *The 2025 Challenge
invites teams to develop algorithms for using electrocardiograms (ECGs) to
identify cases of Chagas disease.*



Chagas disease is a parasitic disease that is primarily transmitted by
triatomine insect bites. It affects an estimated 6.5 million people and
causes nearly 10,000 deaths annually, primarily in Central and South
America. Serological testing can detect Chagas disease and allow for
treatment to slow or prevent damage to the cardiovascular system, but
testing capacity is limited. Chagas disease symptoms may also appear in
ECGs, so automated approaches can help to prioritize individuals for the
limited numbers of serological tests and inform the impacts of and
treatments for Chagas disease.



We have shared training data from the CODE-15% dataset
<https://zenodo.org/records/4916206>, and we will introduce more training
data during the unofficial phase. We have shared example entries and
scoring code in both MATLAB and Python, and we will share more complex
examples during the unofficial phase. We will open the scoring system in
the coming days.



See the Challenge website for more information, rules and deadlines:
https://physionetchallenges.org/2025/.



As in previous years, we have divided the Challenge into two phases: an
unofficial phase and an official phase. The unofficial phase solicits
feedback from the research community (i.e., you) to help us improve the
Challenge for the official phase, *so we require teams to register
and participate in the unofficial phase of the Challenge for prize
eligibility*. Please enter early and often ? we need you to look for quirks
in our data, our scoring system, and otherwise. We are imperfect (and
bandwidth-limited), so please send us suggestions via the forum (see
below). *We rely on the community to help us to improve the quality of the
Challenge each year.*



The culmination of the Challenge will be in Brazil at the annual
meeting of Computing
in Cardiology <http://cinc2025.org/>, where we will present prizes at the
closing ceremony. We're excited to announce that we are *once again
providing an additional prize for teams from the Global South to encourage
representation from underrepresented groups*.



We will post more information on the PhysioNet Challenge website
<http://physionetchallenges.org/2025/> and the Challenge forum
<https://groups.google.com/g/physionet-challenges/> as it becomes
available, or when your input helps us modify the boundaries and content.
Please post questions and comments to the Challenge forum as well. However,
if your question reveals information about your entry, then please email *info
[at] **physionetchallenge.org* <http://physionetchallenge.org/> instead to
help us safeguard the diversity of approaches to the Challenge. We may
share parts of our replies publicly if we feel that all Challengers should
benefit from the information contained in our responses. We will not answer
emails about the Challenge sent to other email addresses.



We thank you for your continued interest and support, and we hope that you
enjoy the 2025 Challenge!



Best of luck!



Gari Clifford (on behalf of The Challenge Team)

Chair, Dept. of Biomedical Informatics, Emory University
Prof. of Biomedical Informatics & Biomedical Engineering
Dept. of Biomedical Informatics, Emory University
Dept. of Biomedical Engineering, Georgia Institute of Technology & Emory
University
Adjunct Faculty, Morehouse School of Medicine


https://PhysioNetChallenges.org/ <https://physionetchallenges.org/>

https://PhysioNet.org/ <https://physionet.org/>

-- 
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 visit
https://groups.google.com/d/msgid/ml-news/b1942219-7087-4153-b00c-d36f97173fddn%40googlegroups.com
<https://groups.google.com/d/msgid/ml-news/b1942219-7087-4153-b00c-d36f97173fddn%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/20250121/f7930ed3/attachment.html>

From awd at cs.cmu.edu  Tue Jan 21 10:52:57 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Tue, 21 Jan 2025 10:52:57 -0500
Subject: Fwd: RI Ph.D. Thesis Defense: Anthony Wertz
In-Reply-To: <CAPfXyxKYcuQAYGoAh50yRzEgmuWk7znXbzLwD_HUVY9-Th4W3w@mail.gmail.com>
References: <CAPfXyxKYcuQAYGoAh50yRzEgmuWk7znXbzLwD_HUVY9-Th4W3w@mail.gmail.com>
Message-ID: <CAJvAoyvGKQ5Pv2AXH1hkaf5dFjbEMCxRtsyuWuZqYY31AfWEcw@mail.gmail.com>

A veteran Autonian just about to become a doctor.

Come and witness this magnificent event!

Artur

---------- Forwarded message ---------
From: Suzanne Muth <lyonsmuth at cmu.edu>
Date: Tue, Jan 21, 2025 at 10:45?AM
Subject: RI Ph.D. Thesis Defense: Anthony Wertz
To: RI People <ri-people at andrew.cmu.edu>


*Date:* 30 January 2025
*Time:* 12:00 p.m. (ET)
*Location:* NSH 3305
*Zoom Link:*
https://cmu.zoom.us/j/95720668348?pwd=zlQghriLapahbjpfpoupIFSNNmkbYu.1
*Type:* Ph.D. Thesis Defense
*Who:* Anthony Wertz
*Title: *Sensorized Soft Materials Systems with Integrated Electronics and
Computing

*Abstract:*

The integration of soft and multifunctional materials in emerging
technologies is becoming more widespread due to their ability to enhance or
improve functionality in ways not possible using typical rigid
alternatives. This trend is evident in various fields. For example,
wearable technologies are increasingly designed using soft materials to
improve modulus compatibility with biological systems and employing
conformable interfaces for electrodes for enhanced signal integrity and
user comfort. Likewise, surgical tools are leveraging soft material systems
to reduce the risk of tissue damage through their inherent compliance. Soft
material systems are also being incorporated into robots to improve safety
in human-robot interactions, as in co-working and assistive applications.

However, the same lack of rigidity and complex constitutive behavior that
make these material systems useful in emerging applications also present
challenges in fully exploiting their capabilities. Soft substrates are
continuously deformable and, without rigid constraints or simplifying
operational assumptions, state inference can be difficult or impossible. In
systems that exploit dynamic material properties, such as those using
shape-memory alloys for actuation or thermoplastic polymers for stiffness
tuning, system behavior is challenging to model from a controls perspective
due to internal states that are difficult or impossible to measure in real
time.

Exploiting these materials effectively requires improved sensor integration
and device co-design. Here I discuss how sensing can be integrated to
harness the inherent functionality of these non-traditional materials while
preserving their novel properties and minimizing unnecessary design
complexity. I first briefly examine integration into existing systems,
highlighting both the potential benefits and challenges of approaching
sensorization in this way. Then I propose a more holistic design approach
that embraces a synergistic relationship between material systems and their
embedded sensors.

*Thesis Committee Members:*
Carmel Majidi, Chair
Oliver Kroemer
Sarah Bergbreiter
Cynthia Hipwell (Texas A&M University)

A draft of the thesis defense document can be found here
<https://drive.google.com/drive/folders/1CHbcnfV7v-XFrW0L715porjhNgD_z1Po?usp=sharing>
.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250121/ddddfb67/attachment-0001.html>

From awd at cs.cmu.edu  Tue Jan 21 15:55:52 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Tue, 21 Jan 2025 15:55:52 -0500
Subject: Fwd: Cluster outage in MR-A
In-Reply-To: <CAO9R1mcnNwB6iRKS35cq_rmAWUS6Y75s6kThS4fYV4AGdqt1tw@mail.gmail.com>
References: <CAO9R1mcnNwB6iRKS35cq_rmAWUS6Y75s6kThS4fYV4AGdqt1tw@mail.gmail.com>
Message-ID: <CAJvAoytfYYGvESBP58d9Z-3DOHoy2fyBbRjjpDu4DnT=xuuQ_A@mail.gmail.com>

fyi

---------- Forwarded message ---------
From: Susan Vigna <sdv at andrew.cmu.edu>
Date: Tue, Jan 21, 2025 at 3:51?PM
Subject: Cluster outage in MR-A
To: Artur Dubrawski <awd at andrew.cmu.edu>, Piotr Bartosiewicz <
pbartosi at andrew.cmu.edu>


Good Afternoon,

  I wanted to give you a heads up that part of the MR-A machine room in
Wean Hall just lost power.  The operations team is working with FMS to get
the power restored as soon as possible.

Right now we do not have an estimate for the power coming back online.  We
are waiting for FMS to arrive to reset the power.

The following clusters are currently affected:

GROGU

Auton
OVEN
CCBI

I will update you again once I know more.

-Susan Vigna
It Manager, Unix Engineering
SCS Computing Facilities
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250121/5ecafe4d/attachment.html>

From awd at cs.cmu.edu  Fri Jan 31 12:36:52 2025
From: awd at cs.cmu.edu (Artur Dubrawski)
Date: Fri, 31 Jan 2025 12:36:52 -0500
Subject: Fwd: CBI Symposium on Responsible & Sustainable AI: March 11-12, 2025
In-Reply-To: <CACb6CQuc9AivAoFCH9hEuH5adO5PMgYbHiMfkW6wjfs3Ut2qnQ@mail.gmail.com>
References: <CAJiSOnZezkQR_vSJQSWRDbJDuAfri0bc2_cRJ6_+BoAo_brwwA@mail.gmail.com>
 <CAJiSOnaYVhjyoHLY4FVgt6Gc3SQ0wqC18ABGkx=2ozWdD7icpw@mail.gmail.com>
 <CACb6CQtFUew6jupGF2_gfg8ooNdWHkkotr9Bn3OWtepTzro+MA@mail.gmail.com>
 <CACb6CQuimcOa7rnrj4sWpDdZzjoXzEGwghxhEUfxtAS3gJ1exw@mail.gmail.com>
 <CACb6CQuc9AivAoFCH9hEuH5adO5PMgYbHiMfkW6wjfs3Ut2qnQ@mail.gmail.com>
Message-ID: <CAJvAoyvkLUbFhm17Ge_CDAULZ+oPEFYWb+mzrKyvAKV9j39eOw@mail.gmail.com>

This is a local event that may be relevant for some of us to attend.
Registration is free.

Artur

---------- Forwarded message ---------
From: Sara Werner <swerner at andrew.cmu.edu>
Date: Fri, Jan 31, 2025 at 12:31?PM
Subject: CBI Symposium on Responsible & Sustainable AI: March 11-12, 2025
To: <scs-people at cs.cmu.edu>


Announcing the
*CBI* *Symposium on Responsible & Sustainable AI*
March 11 - 12, 2025
Bosch Spark Room, 5201 Scott Hall, CMU

Save the date and register now
<https://docs.google.com/forms/d/e/1FAIpQLSfvTNB9cfuL24qzUtI1for__WQeJUckKcA7hC2PTKvlDAwuBA/viewform>
for this two-day summit featuring keynote speakers from CMU, Penn State and
Bosch, who will share cutting-edge research and industry insights on
responsible and sustainable AI.

CBI Fellows will also present the unique work they have had the opportunity
to do as part of the fellowship program, covering topics from privacy,
security, and inclusiveness in AI systems to technologies for environmental
management.

*Keynote speakers include:*
Lorrie Cranor, Valerie Karplus, Zico Kolter, Jonatas Soares dos Santos,
Aarti Singh, Param Singh, Emma Strubell and Shomir Wilson

For a full schedule, please visit the event website.
<https://sites.google.com/andrew.cmu.edu/cbi-resai/schedule>

Contact cbi at andrew.cmu.edu or swerner at andrew.cmu.edu with questions.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/autonlab-users/attachments/20250131/0743c185/attachment.html>