Dr. Gregory Pottie's Lab

Research

Interactive Systems Research Description

Our research focuses on systems in which human interactions are a major component. Examples of interactive systems include education, medicine, games, fitness monitors, self-driving cars, interfaces to consumer electronics, and internet of things applications. These applications share a number of features, of which, the most important from the point of view of algorithmic development is that time-series data is typically undersampled with respect to the requirements for inference, leading to the need for causal models.

For example, consider the education problem. The knowledge graph of a typical engineering course is a directed acyclic graph (DAG) that is rooted in pre- requisites to the course, and proceeds through a sequence of concepts that depend in part on the pre-requisites and some of the concepts introduced earlier. A student’s learning process can also be modeled with a DAG that depends on a number of factors: study skills, mastery of prior content, time commitment, inherent learning ability, confounders (e.g., relationship or family trouble). The education “game” is a cooperative multi-agent game with partial observability. It is cooperative because the students and instructor have similar objectives: good performance on the tests with minimal time commitment. If the tests are carefully designed to measure understanding on the key concepts, then this results in a common objective of student learning. The students can see all the course materials, but with testing alone the instructor gets only periodic and partial sampling of what the student knows. The instructor cannot see into the student’s head; this asymmetry makes it essentially impossible to optimize the mutual strategies. However, there is another vital component in education: the one-on-one interaction in which the student and instructor come to a common understanding of why the student was having difficulty. With symmetry of information, the best intervention (or set of interventions) is usually obvious. This is why one-on-one tutoring has been shown in study after study to be more effective than any other teaching method. Unfortunately, it is not cost-effective. Therefore, the optimization problem in education is to maximize the percentage of a cohort that meets the basic requirement given the time resources of the instructor and the students.

As anyone who has taught in college for any period of time can attest, if one student shows up in office hours with some particular problem in understanding, the chances are high that there are many other students with the same problem. Thus, individual interactions can reveal important information about the cohort, allowing interventions for the class as a whole (e.g., going through another example, reviewing some pre-requisite material, assigning a quiz so that they actually study the concepts of interest). The structure of tests can influence the likelihood of students taking the necessary actions to improve understanding. The traditional midterm/final format does not give timely feedback, and can lead to students being in a deep hole. By contrast, a sequence of quizzes provides reasonably accurate weekly feedback on their progress, and can spur timely action by the students (e.g., group sessions with peers, office hours) that will quickly bring them back on track. Consequently there is not a clean separation between group and individual interventions, but it is clear that there is no way to optimize unless students themselves reveal the reasons for their difficulties to the instructor.

Where are the research challenges? Gathering ground truth is expensive in education, and one cannot try alternative interventions on the same person at the same time, i.e., explore alternative counterfactuals. By contrast, with a generative model, one can construct a simulation in which extensive exploration of counterfactuals is possible. If the generative model is complicated enough, one can investigate questions such as the number of samples/observations required to extend an approximate model, gather sufficient population data to characterize priors for subpopulations, and many other questions related to transfer learning and combining causal and deep learning models. More broadly, we are concerned with how to train models in a sample efficient manner, while preserving out of distribution generalization.

Publications (post 1999)

For list of prior publications, see Dr. Gregory Pottie’s CV

2024

Sunay Bhat, Jeffrey Jiang, Omead Pooladzandi, Alexander Branch, Gregory Pottie
arXiv PrePrint (Under Review)
Omead Pooladzandi, Jeffrey Jiang, Sunay Bhat, Gregory Pottie
arXiv PrePrint

2023

Mahmoud Essalat, Oscar Hernan Madrid Padilla, Vivek Shetty, Gregory Pottie
TechRxiv  ·  28 Apr 2023
Omead Pooladzandi, Jeffrey Jiang, Sunay Bhat, Gregory Pottie
Information Theory and Applications Workshop  ·  15 Mar 2023

2022

Omead Pooladzandi, Yiming Zhou
Conference on Neural Information Processing Systems  ·  28 Jun 2022
Omead Pooladzandi, David Davini, Baharan Mirzasoleiman
International Conference on Machine Learning  ·  28 Jun 2022
Jeffrey Jiang, Omead Pooladzandi, Sunay Bhat, Gregory Pottie
NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research  ·  06 Dec 2022
Sunay Bhat, Jeffrey Jiang, Omead Pooladzandi, Gregory Pottie
Information Theory and Applications Workshop  ·  04 Jul 2022

2020

Manie Tadayon, Gregory Pottie
IEEE Transactions on Education  ·  01 Nov 2020
Aman Mahajan, Gregory Pottie, William Kaiser
ACM Transactions on Computing for Healthcare  ·  02 Mar 2020

2019

Heng Zhao, Leihao Wei, Mona Jarrahi, Gregory Pottie
IEEE Transactions on Terahertz Science and Technology  ·  01 May 2019

2018

Hemant Saggar, Babak Daneshrad, Gregory Pottie
IEEE 88th Vehicular Technology Conference (VTC-Fall)  ·  27 Aug 2018

2017

Ehsan Keramat, Nicholas Kauffroath, Kia Karbasi, Heng Zhao, Babak Daneshrad, Gregory Pottie
IEEE Military Communications Conference (MILCOM)  ·  23 Oct 2017
Yi Jiang, Babak Daneshrad, Gregory Pottie
IEEE Transactions on Wireless Communications  ·  17 Mar 2017

2016

Xiaoxu Wu, Xiaoyu Xu, Yan Wang, William Kaiser, Gregory Pottie
IEEE International Conference on Wearable and Implantable Body Sensor Networks (BSN)  ·  14 Jun 2016

2015

Yi Jiang, Babak Daneshrad, Gregory Pottie
IEEE Military Communications Conference  ·  28 Oct 2015
Hua-I Chang, Vivek Desai, Oscar Santana, Matthew Dempsey, Anchi Su, John Goodlad, Faraz Aghazadeh, Gregory Pottie
Proceedings of the conference on Wireless Health  ·  14 Oct 2015
J. Xu, J. Xu, L. Song, G. Pottie, M. van der Schaar
IEEE Transactions on Biomedical Engineering  ·  12 Feb 2015

2014

Y. Wang, J. Xu, X. Wu, G. Pottie, W. Kaiser
Annual International Conference of the IEEE Engineering in Medicine and Biology Society  ·  06 Sep 2014

2013

Y. Wang, C. Chien, J. Xu, X. Wu, G. Pottie, W. Kaiser
BodyNets '13: Proceedings of the 8th International Conference on Body Area Networks   ·  30 Sep 2013
Y. Wang, C. Chien, J. Xu, G. Pottie, W. Kaiser
IEEE International Conference on Acoustics, Speech and Signal Processing  ·  21 May 2013
H-I Chang, C. Chien, J.Y. Xu, G. J. Pottie
IEEE International Conference on Body Sensor Networks  ·  06 May 2013
X. Wu, Y. Wang, C. Chien, G. Pottie
IEEE International Conference on Body Sensor Networks  ·  06 May 2013
C.C. Chien, J.Y. Xu, H-I Chang, X. Wu, G. J. Pottie
IEEE Workshop on Information Theory and Applications  ·  01 Feb 2013

2012

N. Hajj Chehade, A.P. Ozisik, J. Gomez, F. Ramos, G. Pottie
IEEE Engineering in Medicine and Biology Society Conference  ·  28 Aug 2012
A. Friedman, N. Hajj Chehade, C. Chien, G. Pottie
IEEE Engineering in Medicine and Biology Society Conference  ·  28 Aug 2012
C. Chien, G. Pottie
IEEE Engineering in Medicine and Biology Society Conference  ·  28 Aug 2012
B. Fish, A. Khan, N.H. Chehade, C. Chien, G. Pottie
IEEE International Conference on Acoustics, Speech and Signal Processing  ·  25 Mar 2012

2011

J.Y. Xu, Y. Sun, Z. Wang, W.J. Kaiser, G.J. Pottie
IEEE Wireless Health  ·  10 Oct 2011
Y. Zhao, C.W. Tan, A.S. Avestimehr, S.N. Diggavi, G.J. Pottie
IEEE International Symposium on Information Theory  ·  01 Jul 2011
N. Ruchansky, C. Lochner, E. Do, T. Rawls, N. Hajj Chehade, J. Chien, G. Pottie, W. Kaiser
https://www.researchgate.net/publication/220734474_Monitoring_workspace_activities_using_accelerometers  ·  22 May 2011
D. Bandari, P. Frossard, G. Pottie
IEEE Wireless Communications and Networking Conference  ·  28 Mar 2011
G.J. Pottie
IEEE Information Theory and Applications Workshop  ·  06 Feb 2011

2010

2009

Y. Zhao, G.J. Pottie
IEEE International Symposium on Information Theory  ·  28 Jun 2009
Y. Zhao, G.J. Pottie
IEEE Information Theory and Applications Workshop  ·  09 Feb 2009

2008

A. Pandya, A. Kansal, G. Pottie
IEEE Aerospace Conference  ·  01 Mar 2008
G.J. Pottie
SPIE Defense and Security Symposium  ·  01 Mar 2008
W. Hu, M. Gerla, G.A. Vlantis, G.J. Pottie
IEEE International Workshop on Cognitive Radio and Advanced Spectrum Management  ·  01 Feb 2008
Y.-C. Tong, G.J. Pottie
IEEE Information Theory and Applications Workshop  ·  27 Jan 2008

2007

G. Pottie
IEEE Conf. On Systems, Man and Cybernetics  ·  07 Oct 2007
K. Ni, G. Pottie
IEEE International Symposium on Information Theory  ·  24 Jun 2007
H. Luo, X. Kong, G. Pottie
IEEE International Conference on Acoustics, Speech and Signal Processing  ·  15 Apr 2007

2006

A. Kansal, W. Kaiser, G. Pottie, M. Srivastava, G. Sukhatme
ACM Conference on Embedded Networked Sensor Systems  ·  31 Oct 2006
X. Kong, R. Pon, W. Kaiser, G. Pottie
IEEE International Conference on Acoustics, Speech and Signal Processing  ·  14 May 2006

2005

A. Kansal, A. Ramamoorthy, G. Pottie, M. Srivastava
IEEE International Symposium on Information Theory  ·  05 Sep 2005
H. Luo, G. Pottie
International Conference on Distributed Computing in Sensor Systems  ·  30 Jun 2005
H. Luo, Y. Tong, G. Pottie
IEEE International Conference on Acoustics, Speech and Signal Processing  ·  18 Mar 2005

2004

A. Pandya, G. Pottie
IEEE Asilomar Conference on Signals, Systems and Computers  ·  07 Nov 2004
A. Pandya, H. Luo, G. Pottie
IEEE Asilomar Conference on Signals, Systems and Computers  ·  07 Nov 2004
M. Batalin, M. Rahimi, Y. Yu, D. Liu, A. Kansal, G. Sukhatme, W. Kaiser, M. Hansen, G. Pottie, M. Srivastava, D. Estrin
ACM Conference on Embedded Networked Sensor Systems  ·  03 Nov 2004
A. Pandya, A. Kansal, G. Pottie, M. Srivastava
IEEE Information Theory Society  ·  24 Oct 2004
A. Kansal, M. Rahimi, W. Kaiser, M. Srivastava, G. Pottie, D. Estrin
IEEE Communications Society  ·  04 Oct 2004
S. Natkunanathan, J. Pham, W. Kaiser, G. Pottie
IEEE Communications Society  ·  04 Oct 2004
A. Pandya, A. Kansal, G. Pottie, M. Srivastava
[no publisher info]  ·  29 Sep 2004
A. Kansal, E. Yuen, W. Kaiser, G. Pottie, M. Srivastava
ACM  ·  26 Apr 2004
H. Wang, K. Yao, G. Pottie, D. Estrin
ACM  ·  26 Apr 2004

2003

H. Chen, G. Pottie
IEEE Communications Society  ·  01 Dec 2003
S. Kim, G. Pottie
IEEE Communications Society  ·  01 Dec 2003
A. Pandya, G. Pottie
IEEE  ·  05 Oct 2003
R. Thrasher, G. Pottie
SPIE  ·  01 Aug 2003

2002

R. Thrasher, G. Pottie
AINS  ·  08 May 2002

2001

K. Shoarinejad, F. Paganini, G. Pottie, J. Speyer
IEEE Conf. On Decision and Control  ·  04 Dec 2001
K. Shoarinejad, J. Speyer, G. Pottie
IEEE Communications Society  ·  25 Nov 2001
D. Estrin, L. Girod, G. Pottie, M. Srivastava
IEEE  ·  07 May 2001
Heng Zhao, Gregory Pottie, Babak Daneshrad
IEEE Transactions on Wireless Communications  ·  01 May 2001

2000

M. Ahmed, Y. Tu, G. Pottie
Allerton Conference  ·  04 Oct 2000
G. Kondylis, S. Krishnamurthy, S. Dao, G. Pottie
IEEE  ·  18 Jun 2000
D. Connors, G. Pottie
IEEE  ·  23 Jan 2000

1999

G. Kondylis, G. Pottie
IEEE  ·  05 Dec 1999
T. Yu, D. Chen, G. Pottie, K. Yao
IEEE Workshop on Appl. Of SP to Audio and Acoustics  ·  01 Oct 1999
G. Kondylis, G. Pottie
IEEE  ·  19 Sep 1999