Vickie Winston

Friday, November 4, 2022
10:20 – 11:10 a.m. (CST)
ETB 1020 – **In-person** (Zoom option; Links and PW in syllabus or email)

Dr. Alan Kuhnle
Assistant Professor, Computer Science and Engineering
Texas A&M University

Title: “Scalable and Learned Algorithms for Discrete Optimization”

Talking Points

• Linear-time algorithms for subset selection problems
• RL for learning local search algorithm

Abstract
In this talk, I present the work of the Optimization and Learning Systems Lab on the design of scalable algorithms for optimization problems on big data. In particular, I describe our work on linear-time, parallelizable algorithms for combinatorial optimization problems arising from online social networks. Finally, I give an overview of future directions of the lab, which include augmenting algorithms with learned components to improve practical performance; optimization with incomplete information; and submodular planning.

Biography
Dr. Alan Kuhnle is an Assistant Professor of Computer Science & Engineering at Texas A&M University, where he directs the Optimization and Learning Systems Lab. His work focuses on the design and analysis of scalable algorithms for ubiquitous combinatorial optimization problems arising in data science applications, such as vehicle routing and marketing on social networks. He is the recipient of the First Year Assistant Professor Award at Florida State University in 2020 and his work has led to 34 publications in leading academic journals and conferences. He has served on the program committee of machine learning conferences and is Associate Editor of Journal of Combinatorial Optimization.

Recent TAMU article on Dr. Kuhnle: HERE

More on CESG Seminars: HERE

Please join on Friday, 11/4/22 at 10:20 a.m. in ETB 1020.

Friday, October 28, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr.  Dileep Kalathil
Assistant Professor in the Dept. of Electrical and Computer Engineering
Texas A&M University

Title: “Reinforcement Learning with Robustness and Safety Guarantees”

Talking Points
*How do we develop reinforcement learning algorithms that can overcome the simulation-to-reality gap?
*How do we develop reinforcement learning algorithms that maintain safety constraints during learning?

Abstract
Reinforcement Learning (RL) is the class of machine learning that addresses the problem of learning to control unknown dynamical systems. RL has achieved remarkable success recently in applications like playing games and robotics. However, most of these successes are limited to very structured or simulated environments. When applied to real-world systems, RL algorithms face two fundamental sources of fragility. First, the real-world system parameters can be very different from that of the nominal values used for training RL algorithms. Second, the control policy for any real-world system is required to maintain some necessary safety criteria to avoid undesirable outcomes. Most deep RL algorithms overlook these fundamental challenges which often results in learned policies that perform poorly in the real-world settings. In this talk, I will present two approaches to overcome these challenges. First, I will present an RL algorithm that is robust against the parameter mismatches between the simulation system and the real-world system. Second, I will discuss a safe RL algorithm to learn policies such that the frequency of visiting undesirable states and expensive actions satisfies the safety constraints. I will also briefly discuss some practical challenges due to the sparse reward feedback and the need for rapid real-time adaptation in real-world systems, and the approaches to overcome these challenges.
Robust RL papers: R-P1, R-P2, R-P3
Safe RL papers: S-P1, S-P2, S-P3, S-P4

Biography 
Dr. Dileep Kalathil  is an Assistant Professor in the Department of Electrical and Computer Engineering here at Texas A&M University (TAMU). His main research area is reinforcement learning theory and algorithms, and their applications in communication networks and power systems. Before joining TAMU, he was a postdoctoral researcher in the EECS department at UC Berkeley. He received his Ph.D. from University of Southern California (USC) in 2014, where he won the best Ph.D. Dissertation Prize in the Department of Electrical Engineering. He received his M. Tech. from IIT Madras, where he won the award for the best academic performance in the Electrical Engineering Department. He received the NSF CRII Award in 2019 and the NSF CAREER award in 2021. He is a senior member of IEEE.

More information on Dr. Kalathil can be found HERE.

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

* Friday, 10/28/22 at 10:20 a.m. via Zoom *

Friday, ????  2023
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr.  Jiantao Jiao
Assistant Professor in the Dept. of EECS and the Dept. of Statistics 
University of California, Berkeley

Title: “Optimal Offline RL with General Function Approximation via Augmented Lagrangian”

Talking Points
*Statistically optimal offline RL algorithm with general function approximators such as neural networks
*Bypassing the need for Uncertainty quantification in handling partial data coverage through marginalized importance sampling (MIS)
*Augmented Lagrangian Method (ALM) combined with MIS gives optimal conservative offline RL without any hand-designed behavior regularization  or oracle uncertainty quantification

Abstract
Offline reinforcement learning (RL), which refers to decision-making from a previously-collected dataset of interactions, has received significant attention over the past years. Much effort has focused on improving offline RL practicality by addressing the prevalent issue of partial data coverage through various forms of conservative policy learning. While the majority of algorithms do not have finite-sample guarantees, several provable conservative offline RL algorithms are designed and analyzed within the single-policy concentrability framework that handles partial coverage. Yet, in the nonlinear function approximation setting where confidence intervals are difficult to obtain, existing provable algorithms suffer from computational intractability, prohibitively strong assumptions, and suboptimal statistical rates. In this paper, we leverage the marginalized importance sampling (MIS) formulation of RL and present the first set of offline RL algorithms that are statistically optimal and practical under general function approximation and single-policy concentrability, bypassing the need for uncertainty quantification. We identify that the key to successfully solving the sample-based approximation of the MIS problem is ensuring that certain state occupancy validity constraints are nearly satisfied. We enforce these constraints by a novel application of the augmented Lagrangian method and prove the following result: with MIS formulation, augmented Lagrangian is enough for statistically optimal offline RL. In stark contrast to prior algorithms that induce additional conservatism through methods such as behavior regularization, our approach provably eliminates this need and reinterprets regularizers as “enforcers of state occupancy validity” than “promoters of conservatism”.

Biography 
Dr. Jiantao Jiao is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences and Department of Statistics at the University of California, Berkeley. He co-directs the Center for the Theoretical Foundations of Learning, Inference, Information, Intelligence, Mathematics, and Microeconomics at Berkeley (CLIMB), is a member of the Berkeley Artificial Intelligence Research (BAIR) Lab, and the Berkeley Laboratory for Information and System Sciences (BLISS). He received his Ph.D. from Stanford University in 2018. He is a recipient of the Presidential Award of Tsinghua University and the Stanford Graduate Fellowship. He was a semi-plenary speaker at ISIT 2015 and a co-recipient of the MobiHoc 2019 best paper award.

More information on Dr. Jiao can be found HERE.

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

* Friday, 10/28/22 at 10:20 a.m. via Zoom *

Friday, October 7, 2022
10:20 – 11:10 a.m. (CST)
ETB 1020 – **In-person** (Zoom option; Links and PW in syllabus or email)

Dr. George T. Ligler
Professor, Multidisciplinary Engineering
Texas A&M University

Title: “Automatic Dependent Surveillance—Broadcast (ADS-B): A Major Aviation System’s Conception, Development, and Operational Implementation”

Talking Points

• In order to be successful, computer systems engineers need to learn to work with the full set of project stakeholders.
• The “best” technical solution to a problem is often not the one employed or that should be employed–broaden your view of he “trade space”!
• Computer system engineers have the opportunity to constantly learn while being instrumental in “getting things done”.
• We have a worldwide shortage of interdisciplinary computer systems engineers.

Abstract
ADS-B provides the largest improvement in air traffic surveillance since the advent of radar in the 1940’s. This presentation discusses the 27-year journey of the ADS-B System from concept development to operational implementation on over 100,000 aircraft in the U.S. National Airspace System alone. The role of interdisciplinary computer system engineering in the development and implementation of this high-impact system is highlighted.

Biography
Dr. George T. Ligler is a Professor and Dean’s Excellence Chair of Multidisciplinary Engineering at Texas A&M University. He is also the proprietor of GTL Associates, a consultancy which has provided systems integration/engineering and product management services in multiple fields to over 40 clients on three continents. An elected member of the U.S. National Academy of Engineering, Dr. Ligler is a member and past Chair of the Academy’s Section 12, Special Fields and Interdisciplinary Engineering.  With regard to aviation, he has served on one or more aviation standards development committees since 1992 and since 2005 has been the Co-Chair of RTCA Special Committee 159, Navigation Equipment Using the Global Navigation Satellite System (GNSS). He has been recognized with RTCA’s highest award, the Achievement Award, in 2006 and 2017 and was a co-recipient of the Air Traffic Control Association’s 2015 Chairman’s Citation Award of Merit to the NextGen Institute’s Equip 2020 Initiative for ADS-B.  Dr. Ligler has also participated in nine National Academies of Sciences, Engineering, and Medicine committees advising the Departments of Transportation, Treasury, and Commerce, and is a current member of the Academies’ Aeronautics and Space Engineering Board. He holds a doctorate in mathematics from the University of Oxford, with his studies supported by a Rhodes Scholarship.

Recent TAMU article on Dr. Ligler: HERE

More on CESG Seminars: HERE

Please join on Friday, 10/7/22 at 10:20 a.m. in ETB 1020.

 

Friday, October 21, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr.  Bhuvana Krishnaswamy
Assistant Professor in Electrical and Computer Engineering
University of Wisconsin-Madison

Title: “Scalability in Low Power Wide Area Networks”

Talking Points:
* Long range and low power requirements have contrasting demands on the network.
* Current LPWAN solutions do not satisfy the large-scale needs of practical deployments.

Abstract
Wireless data delivery over long distance is power consuming and challenging for large-scale deployments. Low-power wide area networks (LPWAN) are increasingly in need to develop wireless solutions that satisfy the following requirements (1) Increased battery life, (2) Longer communication range, (3) Large-Scale, and (4) Low-cost. Existing strategies for addressing low-power and long-range do not efficiently address all of these in a large-scale network. In this talk, the fundamental challenges in meeting the above needs of LPWANs will be identified. Collision resolution approaches to meet the demands of large-scale, commercially available LPWANs – LoRa – will be the focus of this talk.

Biography 
Dr. Bhuvana Krishnaswamy is an Assistant Professor in the Department of Electrical and Computer Engineering at University of Wisconsin-Madison. She obtained her MS and Ph.D. in from Georgia Institute of Technology. She is the recipient of NSF CAREER Award, N2Women Rising Star Award, and the Grainger Faculty Scholarship Award. Her research interests are in low-power wireless communication and its challenges in practical deployments. Additional details about her research and team can be found at https://uwconnect.ece.wisc.edu/

More information on Dr. Krishnaswamy can be found HERE.

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

* Friday, 10/21/22 at 10:20 a.m. via Zoom *

Friday, October 14, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr.  Aditya Mahajan,
Associate Professor in Electrical and Computer Engineering
McGill University – Montreal, Canada

Title: “Approximate Planning and Learning for Partially Observed Systems ”

Talking Points:
* Propose a theoretical framework–based on the fundamental notion of information state–for approximate planning and learning in partially observed systems.
* Define an approximate information state (AIS) and a corresponding approximate dynamic program (ADP).
* Bound the error in using the policy obtained by the solution of the AIS-based ADP.
* Develop RL algorithms based on these bounds and illustrate that they perform well in high-dimensional partially observed grid-world environments.

Abstract
Reinforcement learning (RL) provides a conceptual framework for designing agents which learn to act optimally in unknown environments. RL has been successfully used in various applications ranging from robotics, industrial automation, finance, healthcare, and natural language processing. The success of RL is based on a solid foundation of combining the theory of exact and approximate Markov decision processes (MDPs) with iterative algorithms that are guaranteed to learn an exact or approximate action-value function and/or an approximately optimal policy. However, for the most part, the research on RL theory is focused on systems with full state observations.

In various applications including robotics, finance, and healthcare, the agent only gets a partial observation of the state of the environment. In this talk, I will describe a new framework for approximate planning and learning for partially observed systems based on the notion of approximate information state. The talk will highlight the strong theoretical foundations of this framework, illustrate how many of the existing approximation results can be viewed as a special case of approximate information state, and provide empirical evidence which suggests that this approach works well in practice.

Joint work with Jayakumar Subramanian, Amit Sinha, Raihan Seraj, and Erfan Seyedsalehi

Biography 
Dr. Aditya Mahajan is Associate Professor of Electrical and Computer Engineering at McGill University, Montreal, Canada. He is affiliated with the McGill Center of Intelligent Machines (CIM), Montreal Institute of Learning Algorithms (Mila), and Group for research in decision analysis (GERAD). He received the B.Tech degree in Electrical Engineering from the Indian Institute of Technology, Kanpur, India in 2003 and the MS and PhD degrees in Electrical Engineering and Computer Science from the University of Michigan, Ann Arbor, USA in 2006 and 2008.

He is the recipient of the 2015 George Axelby Outstanding Paper Award, the 2016 NSERC Discovery Accelerator Award, the 2014 CDC Best Student Paper Award (as supervisor), and the 2016 NecSys Best Student Paper Award (as supervisor). His principal research interests are learning and control of decentralized stochastic system.

More information on Dr. Mahajan HERE.

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

* Friday, 10/14/22 at 10:20 a.m. via Zoom *

 

 

Friday, September 30, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr. Aditya Akella
Regents Chair in Computer Sciences and Professor at UT Austin
Google Software Engineer

Title: “Cloud Velocity Networking: How We Got Here and Where We’re Headed”

Talking Points:

• Cloud services are driving the need for networking velocity
• Programmable network devices are being rapidly developed to serve this need
• We will cover state-of-the-art and open problems in new programmable device architectures and programming models 

Abstract

Over the past few years, networking advances have played a crucial role in enabling high-velocity, agile cloud computing deployments, and use cases. Technologies such as software-defined networking, network virtualization, and high-bisection fabrics have simplified cloud design and operation, brought exciting new workloads to the cloud, and helped lower the bar to cloud adoption. Networking is poised to bring even more interesting and fundamental transformations to the cloud over the next few years, enabling even greater velocity and diversity of use cases, without compromising performance, manageability, and high assurance. In this talk, I will describe some of the key “enabler” networking ideas, spanning high-performance fabrics and network stacks, programmable hardware, abstractions for network automation, and novel inter-domain protocols and services. I will discuss the tantalizing opportunities these ideas offer for future cloud computing, and the fundamental new research and practical challenges they introduce. I will conclude my talk with observations on what it would take for our research community to make rapid and meaningful progress in this space.

Biography

Dr. Aditya Akella is a Regents Chair Professor of Computer Science at UT Austin and a software engineer at Google. Aditya received his B. Tech. from IIT Madras (2000), and PhD from CMU (2005). His research spans computer systems and networking, with a focus on programmable networks, formal methods in systems, and systems for big data and machine learning. His work has influenced the infrastructure of some of the world’s largest online service providers. Aditya has received many awards for his contributions, including ACM SIGCOMM Test of Time Award (2022), selection as a finalist for the US Blavatnik National Award for Young Scientists (2020 and 2021), UW-Madison “Professor of the Year” award (2019 and 2017), IRTF Applied Networking Research Prize (2015), SIGCOMM Rising Star award (2014), NSF CAREER award (2008), and several best paper awards.

More Info on Dr. Akella at: https://www.cs.utexas.edu/~akella/ 

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

Please join on Friday, 9/30/22 at 10:20 a.m. via Zoom.

 

 

Friday, September 16, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr. Joerg Widmer
Research Professor and Research Director of IMDEA Networks
Madrid, Spain

Title: “Millimeter-Wave Joint Communication and Sensing and Location-based Network Control”

Talking Points:

• Practical challenges of millimeter-wave communications
• Benefits of millimeter-wave frequencies for high-precision sensing and localization

Abstract

The high bandwidth available at millimeter-wave frequencies allows for very high data rates, and the latest wireless technologies already exploit this part of the radio spectrum to achieve rates of several GBit/s per user. Communication at these frequencies typically uses directional antennas which brings about interesting challenges to align antenna beams. Given the high penetration loss, most obstacles (e.g., a person) also completely block the signal. This results in a very dynamic radio environment and channels may appear and disappear over very short time intervals. This seminar highlights some approaches to deal with these networking challenges. The very large bandwidth available at mm-wave frequencies also allows to design highly accurate location systems, and such location information be used to facilitate beam training, optimize access point association, and predict future blockage. We discuss how to implement such millimeter-wave location systems and present network optimization mechanisms based on simultaneous localization and mapping of the environment.

Finally, the information about the wireless channel of millimeter-wave systems can also be used for highly accurate environment sensing. We discuss how to use communication hardware to perform zero-cost monitoring of human movement and activities in indoor spaces (rather than using dedicated radars). We show that access points can be retrofitted to perform radar-like extraction of the micro-Doppler effects caused by the motion of multiple human subjects. We then use this to achieve fine-grained sensing applications such as simultaneous activity recognition and person identification. We will specifically focus on the practical implementation aspects, testbed design and experimental results with such systems.

Biography

Dr. Joerg Widmer is a Research Professor and Research Director of IMDEA Networks in Madrid, Spain. Before, he held positions at DOCOMO Euro-Labs in Munich, Germany and EPFL, Switzerland. He was a visiting researcher at the International Computer Science Institute in Berkeley, USA, University College London, UK, and TU Darmstadt, Germany. His research focuses on wireless networks, ranging from extremely high frequency millimeter-wave communication and MAC layer design to mobile network architectures. Joerg Widmer authored more than 200 conference and journal papers and three IETF RFCs, and holds 14 patents. He was awarded an ERC consolidator grant, the Friedrich Wilhelm Bessel Research Award of the Alexander von Humboldt Foundation, a Mercator Fellowship of the German Research Foundation, a Spanish Ramon y Cajal grant, as well as nine best paper awards. He is an IEEE Fellow and Distinguished Member of the ACM.

More Info on Dr. Widmer at: https://networks.imdea.org/team/imdea-networks-team/people/joerg-widmer/

More info. on past and future CESG Seminars at CESG Seminars (tamu.edu)

Please join on Friday, 9/16/22 at 10:20 a.m. via Zoom.

 

 

Friday, September 9, 2022
10:20 – 11:10 a.m. (CST)
Virtual via Zoom: https://tamu.zoom.us/j/93347193479 (password in emails or syllabus)

Dr. Subhonmesh Bose
Assistant Professor, University of Illinois Urbana Champaign

Title: “Modeling Risk in Power System Operations and Planning”

Talking Points:

• How you model risk should depend on how you can optimize against it
• Primal-dual algorithms for risk-sensitive optimization

Abstract

Integration of variable renewable and distributed energy resources in the grid makes demand and supply conditions uncertain. In this talk, we will first explore electricity market design for daily operations that explicitly models power delivery risks and system constraint violation risks. Then, we will discuss the distributed solar hosting capacity problem that considers said risks in electricity infrastructure planning. Throughout the talk, we will encode risks via the conditional value at risk (CVaR) measure, properties of which allow efficient, often customized, algorithm design for optimization, and facilitate the definition of economically meaningful prices in market design contexts.

Biography

Dr. Subhonmesh Bose is an Assistant Professor and Stanley Helm Fellow in the Department of Electrical and Computer Engineering at UIUC. His research focuses on facilitating the integration of renewable and distributed energy resources into the grid, leveraging tools from optimization, control and game theory. Before joining UIUC, he was a postdoctoral fellow at the Atkinson Center for Sustainability at Cornell University. Prior to that, he received his MS and Ph.D. degrees from Caltech in 2012 and 2014, respectively. He received the NSF CAREER Award in 2021. His research projects have been supported by grants from NSF, PSERC, Siebel Energy Institute and C3.ai, among others.

More Info: http://boses.ece.illinois.edu/

Please join on Friday, 9/9/22 at 10:20 a.m. via Zoom.

 

 

Friday, September 23, 2022
10:20 – 11:10 a.m. (CST)
ETB 1020 – **In-person** (or Zoom for those receiving emails)

Dr. Biswajit Ray
Associate Professor, Dept. of ECE at The University of Alabama

Title: “Intelligent Data Storage Systems for Cyber-Security, Extreme-Reliability and Edge-Computing”

Talking Points:

• Monolithic 3D NAND Flash technology is the industry’s workhorse for high density data storage
• Data security and user privacy are at stake in Flash storage
• Radiation environment makes Flash storage vulnerable

Abstract

Even though solid-state storage technology has seen unprecedented growth in bit-density over the last few decades, emerging artificial intelligence and edge computing applications present new challenges related to security, resilience, and energy-efficiency. These challenges can only be addressed through innovative system design concepts that aptly utilize the physical properties of storage media. While the traditional storage system mainly relies on technology-agnostic algorithmic functions for the ease of portability, such design underutilizes the rich physical properties of the storage media. Thus, state-of-the art storage solutions are inadequate to ensure resilience, energy efficiency, system security and end-user privacy at the edge nodes and extreme environments.

In this talk, I will present a few innovative techniques that will bridge the gap between device and system design approaches to open-up new opportunities for enhancing resilience, security, and energy efficiency of future edge computing/storage applications. I will illustrate system-level techniques to define hardware security primitives using physical properties of commercial flash memory. I will share my experimental research findings on the radiation effects on the 3D NAND storage and system-level countermeasures. Finally, I will present a conceptual framework for energy-efficient computing and storage using flash memory for error-tolerant applications.

Biography

Dr. Biswajit Ray is an Associate Professor of Electrical and Computer Engineering with the University of Alabama in Huntsville (UAH), AL, USA, where he leads Hardware Security and Reliability Laboratory. Dr. Ray received Ph.D. from Purdue University, West Lafayette, IN and then he worked in SanDisk Corporation, Milpitas, California developing 3D NAND Flash memory technology. Dr. Ray holds 17 U.S. issued patents on non-volatile memory systems, published more than 50 research papers in international journals and conferences. Dr. Ray is a recipient of NSF CAREER Award (2022), NSF EPSCoR Research Fellow (2020) and Outstanding Faculty Award (2022) at UAH.

References:
[1] S. Sakib, A. Milenkovic, and B. Ray, “Flash Watermark: An Anti-Counterfeiting Technique for NAND Flash Memories,” IEEE Transaction on Electron Devices, vol. 67, no. 10, pp. 4172–4177, 2020.
[2] P. Kumari, S. Huang, M. Wasiolek, K. Hattar, and B. Ray, “Layer Dependent Bit Error Variation in 3-D NAND Flash Under Ionizing Radiation,” IEEE Transactions on Nuclear Science, vol. 67, no. 9, pp. 2021-2027, 2020.
[3] M. Hasan and B. Ray, “Data Recovery from “Scrubbed” NAND Flash Storage: Need for Analog Sanitization,” in Proc. of the 29^th USENIX Security Symposium, Boston, MA, Aug. 2020.

Google Page: https://sites.google.com/a/uah.edu/ray_biswajit 

Please join on Friday, 9/23/22 at 10:20 a.m. in ETB 1020.

Host: Dr. Sunil Khatri