ArtIAMAS Seminar Series

We study a new approach to accelerating machine learning problems in this talk. The system comprises multiple agents, each with a set of local data points and an associated local cost function. The agents are connected to a server, and there is no inter-agent communication. The agents’ goal is to learn a parameter vector that optimizes the aggregate of their local costs without revealing their local data points. We propose an iterative preconditioning technique to mitigate the deleterious effects of the cost function’s conditioning on the convergence rate of distributed gradient-descent. Unlike the conventional preconditioning techniques, the pre-conditioner matrix in our proposed technique updates iteratively to facilitate implementation on the distributed network. In the particular case when the minimizer of the aggregate cost is unique, our algorithm converges super linearly. We demonstrate our algorithm’s superior performance in machine learning, distributed estimation, and beamforming problems, thereby demonstrating the proposed algorithm’s efficiency for distributively solving nonconvex optimization problems.

Dr. Nikhil Chopra is a Professor in the Department of Mechanical Engineering at the University of Maryland, College Park. He received a Bachelor of Technology (Honors) degree in Mechanical Engineering from the Indian Institute of Technology, Kharagpur, India, in 2001, an M.S. degree in General Engineering in 2003, and a Ph.D. degree in Systems and Entrepreneurial Engineering in 2006 from the University of Illinois at Urbana-Champaign. His current research interests are in the areas of nonlinear control, robotics, and machine learning. He is the co-author of the book Passivity-Based Control and Estimation in Networked Robotics. He is currently an Associate Editor of Automatica and was previously an Associate Editor of IEEE Transactions on Control of Network Systems and IEEE Transactions on Automatic Control.

As autonomous systems are fielded in unknown, dynamic, potentially contested conditions, they will need to operate with partial, uncertain information. Successful long-term deployments will need agents to reason about their energy logistics and require careful coordination between robots with vastly different energetics (e.g., air and ground platforms), which is especially challenging in the face of uncertainty. To make matters complicated, communication between the agents may not always be available. In this talk, I will present our ongoing ArtIAMAS work on risk-aware route planning and coordination algorithms that can reason about uncertainty in a provable fashion to enable long-term autonomous deployments.

Dr. Pratap Tokekar is an Assistant Professor in the Department of Computer Science and UMIACS at the University of Maryland. Between 2015 and 2019, he was an Assistant Professor at the Department of Electrical and Computer Engineering at Virginia Tech. Previously, he was a Postdoctoral Researcher at the GRASP lab of University of Pennsylvania. He obtained his Ph.D. in Computer Science from the University of Minnesota in 2014 and Bachelor of Technology degree in Electronics and Telecommunication from College of Engineering Pune, India in 2008. He is a recipient of the NSF CAREER award (2020) and CISE Research Initiation Initiative award (2016). He serves as an Associate Editor for the IEEE Transactions on Robotics, IEEE Transactions of Automation Science & Engineering, and the ICRA and IROS Conference Editorial Board. http://raaslab.org/

To achieve the goal of building natural language processing systems that help real-world users with tasks, such systems need to be able to communicate bidirectionally with their users. This includes systems describing and explaining their solutions and their difficulties. This also involves systems that can learn from a wide variety of feedback — including language — that a user may provide. I’ll describe our past and ongoing work in this space, and how it ties in to our current ArtIAMAS project on systems to help triage documents efficiently and effectively.

Dr. Hal Daumé III is a Perotto Professor in Computer Science and Language Science at the University of Maryland, College Park; he has a joint appointment as a Senior Principal Researcher at Microsoft Research, New York City. His primary research interest is in developing new learning algorithms for prototypical problems that arise in the context of natural language processing and artificial intelligence, with a focus on interactive learning and understanding and minimizing social harms that can be caused or exacerbated by computational systems.

Sophisticated sensor processing at the network edge opens up many new applications for extraction and exploitation of knowledge from diverse sensing modalities. However, these applications must typically satisfy stringent constraints on real-time performance and energy efficiency, and they involve complex trade-offs among processing that is performed at the edge, processing that is offloaded to more powerful resources (in the fog or cloud), and the communication required for such offloading. In this talk, I will discuss models and methods to explore the opportunities and address the challenges associated with pushing complex sensor processing tasks to the edge. Core themes of the presentation will include (1) model-based design methodologies, particularly those based on dataflow models of computation, for design and implementation of complex embedded hardware/software systems, and (2) design optimization techniques for efficiently utilizing multicore embedded processing platforms under stringent constraints on performance and energy consumption

Dr. Shuvra S. Bhattacharyya is a Professor in the Department of Electrical and Computer Engineering at the University of Maryland, College Park. He holds a joint appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS) and is affiliated with the Maryland Crime Research and Innovation Center (MCRIC). He also holds a part-time visiting position as Chair of Excellence in Design Methodologies and Tools at the National Institute for Applied Sciences (INSA) in Rennes, France. His research interests include signal processing, embedded systems, electronic design automation, machine learning, wireless communication, and wireless sensor networks. He received the Ph.D. degree from the University of California at Berkeley. He has held industrial positions as a Researcher at the Hitachi America Semiconductor Research Laboratory (San Jose, California), and Compiler Developer at Kuck & Associates (Champaign, Illinois). He is a Fellow of the IEEE and recipient of the NSF CAREER Award.

In this talk we will address the issue of building resilient systems in the face of cyberattacks. We will present defense mechanism for cyberattacks using a 3-tier architecture that can be used to secure army assets and tactical information. The top tier represents the front-end where autonomous sensing and inferencing through AI models take place by UAVs, UGVs, etc. We will illustrate how models can be defended against data poisoning attacks. In the middle tier we focus on building cyber defense against attacks in federated learning environments, where models are trained on large corpus of decentralized data without transferring raw over a communication channel. The bottom tier represents back-end servers that train deep learning models with large amounts of data that can subsequently be pushed to the edge for inferencing. We will demonstrate how adaptive models can be developed for detecting and preventing various types of attacks at this level.

Dr. Aryya Gangopadhyay is a Professor in the Information Systems department at the University of Maryland Baltimore County. Dr. Gangopadhyay has a courtesy appointment as a Professor in Computer Science and Electrical Engineering at UMBC. He is also the Director of the Center Realtime Sensing and Autonomy (CARDS) at UMBC. His research interests include adversarial machine learning at the edge, cybersecurity, and smart cities. He has graduated 16 PhD students and is currently mentoring several others at UMBC. He has published over 125 peer-reviewed research articles and has received extramural support from ARL, NSF, NIST, Department of Education, and IBM.

In today’s technology environment, information is abundant, dynamic, and heterogeneous in nature. Automated filtering and prioritization of information is based on the distinction between whether the information adds substantial value toward one’s goal or not. Contextual multi-armed bandit has been widely used for learning to filter contents and prioritize according to user interest or relevance. Learn-to-Rank technique optimizes the relevance ranking on items, allowing the contents to be selected accordingly. We propose a novel approach to top-K rankings under the contextual multi-armed bandit framework. We model the stochastic reward function with a neural network to allow non-linear approximation to learn the relationship between rewards and contexts. We demonstrate the approach and evaluate the performance of learning from the experiments using real world data sets in simulated scenarios. Empirical results show that this approach performs well under the complexity of a reward structure and high dimensional contextual features.

Dr. Jade Freeman is the Chief of the Battlefield Information Systems Branch, DEVCOM U.S. Army Research Laboratory (ARL), overseeing military information systems and analysis research projects. Prior to joining ARL, Dr. Freeman served as the Senior Statistician for the Chief of Staff at the Department of Homeland Security, Office of Cybersecurity and Communications, currently known as The Cybersecurity and Infrastructure Security Agency (CISA), Dr. Freeman obtained her Ph. D. in Statistics from George Washington University. 

As autonomous systems are fielded in unknown, dynamic, potentially contested conditions, they will need to operate with partial, uncertain information. Successful long-term deployments will need agents to reason about their energy logistics and require careful coordination between robots with vastly different energetics (e.g., air and ground platforms), which is especially challenging in the face of uncertainty. To make matters complicated, communication between the agents may not always be available. In this talk, I will present our ongoing ArtIAMAS work on risk-aware route planning and coordination algorithms that can reason about uncertainty in a provable fashion to enable long-term autonomous deployments.

Dr. Pratap Tokekar is an Assistant Professor in the Department of Computer Science and UMIACS at the University of Maryland. Between 2015 and 2019, he was an Assistant Professor at the Department of Electrical and Computer Engineering at Virginia Tech. Previously, he was a Postdoctoral Researcher at the GRASP lab of University of Pennsylvania. He obtained his Ph.D. in Computer Science from the University of Minnesota in 2014 and Bachelor of Technology degree in Electronics and Telecommunication from College of Engineering Pune, India in 2008. He is a recipient of the NSF CAREER award (2020) and CISE Research Initiation Initiative award (2016). He serves as an Associate Editor for the IEEE Transactions on Robotics, IEEE Transactions of Automation Science & Engineering, and the ICRA and IROS Conference Editorial Board. http://raaslab.org/

To achieve the goal of building natural language processing systems that help real-world users with tasks, such systems need to be able to communicate bidirectionally with their users. This includes systems describing and explaining their solutions and their difficulties. This also involves systems that can learn from a wide variety of feedback — including language — that a user may provide. I’ll describe our past and ongoing work in this space, and how it ties in to our current ArtIAMAS project on systems to help triage documents efficiently and effectively.

Dr. Hal Daumé III is a Perotto Professor in Computer Science and Language Science at the University of Maryland, College Park; he has a joint appointment as a Senior Principal Researcher at Microsoft Research, New York City. His primary research interest is in developing new learning algorithms for prototypical problems that arise in the context of natural language processing and artificial intelligence, with a focus on interactive learning and understanding and minimizing social harms that can be caused or exacerbated by computational systems.

Sophisticated sensor processing at the network edge opens up many new applications for extraction and exploitation of knowledge from diverse sensing modalities. However, these applications must typically satisfy stringent constraints on real-time performance and energy efficiency, and they involve complex trade-offs among processing that is performed at the edge, processing that is offloaded to more powerful resources (in the fog or cloud), and the communication required for such offloading. In this talk, I will discuss models and methods to explore the opportunities and address the challenges associated with pushing complex sensor processing tasks to the edge. Core themes of the presentation will include (1) model-based design methodologies, particularly those based on dataflow models of computation, for design and implementation of complex embedded hardware/software systems, and (2) design optimization techniques for efficiently utilizing multicore embedded processing platforms under stringent constraints on performance and energy consumption

Dr. Shuvra S. Bhattacharyya is a Professor in the Department of Electrical and Computer Engineering at the University of Maryland, College Park. He holds a joint appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS) and is affiliated with the Maryland Crime Research and Innovation Center (MCRIC). He also holds a part-time visiting position as Chair of Excellence in Design Methodologies and Tools at the National Institute for Applied Sciences (INSA) in Rennes, France. His research interests include signal processing, embedded systems, electronic design automation, machine learning, wireless communication, and wireless sensor networks. He received the Ph.D. degree from the University of California at Berkeley. He has held industrial positions as a Researcher at the Hitachi America Semiconductor Research Laboratory (San Jose, California), and Compiler Developer at Kuck & Associates (Champaign, Illinois). He is a Fellow of the IEEE and recipient of the NSF CAREER Award.

In this talk we will address the issue of building resilient systems in the face of cyberattacks. We will present defense mechanism for cyberattacks using a 3-tier architecture that can be used to secure army assets and tactical information. The top tier represents the front-end where autonomous sensing and inferencing through AI models take place by UAVs, UGVs, etc. We will illustrate how models can be defended against data poisoning attacks. In the middle tier we focus on building cyber defense against attacks in federated learning environments, where models are trained on large corpus of decentralized data without transferring raw over a communication channel. The bottom tier represents back-end servers that train deep learning models with large amounts of data that can subsequently be pushed to the edge for inferencing. We will demonstrate how adaptive models can be developed for detecting and preventing various types of attacks at this level.

Dr. Aryya Gangopadhyay is a Professor in the Information Systems department at the University of Maryland Baltimore County. Dr. Gangopadhyay has a courtesy appointment as a Professor in Computer Science and Electrical Engineering at UMBC. He is also the Director of the Center Realtime Sensing and Autonomy (CARDS) at UMBC. His research interests include adversarial machine learning at the edge, cybersecurity, and smart cities. He has graduated 16 PhD students and is currently mentoring several others at UMBC. He has published over 125 peer-reviewed research articles and has received extramural support from ARL, NSF, NIST, Department of Education, and IBM.

In today’s technology environment, information is abundant, dynamic, and heterogeneous in nature. Automated filtering and prioritization of information is based on the distinction between whether the information adds substantial value toward one’s goal or not. Contextual multi-armed bandit has been widely used for learning to filter contents and prioritize according to user interest or relevance. Learn-to-Rank technique optimizes the relevance ranking on items, allowing the contents to be selected accordingly. We propose a novel approach to top-K rankings under the contextual multi-armed bandit framework. We model the stochastic reward function with a neural network to allow non-linear approximation to learn the relationship between rewards and contexts. We demonstrate the approach and evaluate the performance of learning from the experiments using real world data sets in simulated scenarios. Empirical results show that this approach performs well under the complexity of a reward structure and high dimensional contextual features.

Dr. Jade Freeman is the Chief of the Battlefield Information Systems Branch, DEVCOM U.S. Army Research Laboratory (ARL), overseeing military information systems and analysis research projects. Prior to joining ARL, Dr. Freeman served as the Senior Statistician for the Chief of Staff at the Department of Homeland Security, Office of Cybersecurity and Communications, currently known as The Cybersecurity and Infrastructure Security Agency (CISA), Dr. Freeman obtained her Ph. D. in Statistics from George Washington University. 

As autonomous systems are fielded in unknown, dynamic, potentially contested conditions, they will need to operate with partial, uncertain information. Successful long-term deployments will need agents to reason about their energy logistics and require careful coordination between robots with vastly different energetics (e.g., air and ground platforms), which is especially challenging in the face of uncertainty. To make matters complicated, communication between the agents may not always be available. In this talk, I will present our ongoing ArtIAMAS work on risk-aware route planning and coordination algorithms that can reason about uncertainty in a provable fashion to enable long-term autonomous deployments.

Dr. Pratap Tokekar is an Assistant Professor in the Department of Computer Science and UMIACS at the University of Maryland. Between 2015 and 2019, he was an Assistant Professor at the Department of Electrical and Computer Engineering at Virginia Tech. Previously, he was a Postdoctoral Researcher at the GRASP lab of University of Pennsylvania. He obtained his Ph.D. in Computer Science from the University of Minnesota in 2014 and Bachelor of Technology degree in Electronics and Telecommunication from College of Engineering Pune, India in 2008. He is a recipient of the NSF CAREER award (2020) and CISE Research Initiation Initiative award (2016). He serves as an Associate Editor for the IEEE Transactions on Robotics, IEEE Transactions of Automation Science & Engineering, and the ICRA and IROS Conference Editorial Board. http://raaslab.org/

To achieve the goal of building natural language processing systems that help real-world users with tasks, such systems need to be able to communicate bidirectionally with their users. This includes systems describing and explaining their solutions and their difficulties. This also involves systems that can learn from a wide variety of feedback — including language — that a user may provide. I’ll describe our past and ongoing work in this space, and how it ties in to our current ArtIAMAS project on systems to help triage documents efficiently and effectively.

Dr. Hal Daumé III is a Perotto Professor in Computer Science and Language Science at the University of Maryland, College Park; he has a joint appointment as a Senior Principal Researcher at Microsoft Research, New York City. His primary research interest is in developing new learning algorithms for prototypical problems that arise in the context of natural language processing and artificial intelligence, with a focus on interactive learning and understanding and minimizing social harms that can be caused or exacerbated by computational systems.

Sophisticated sensor processing at the network edge opens up many new applications for extraction and exploitation of knowledge from diverse sensing modalities. However, these applications must typically satisfy stringent constraints on real-time performance and energy efficiency, and they involve complex trade-offs among processing that is performed at the edge, processing that is offloaded to more powerful resources (in the fog or cloud), and the communication required for such offloading. In this talk, I will discuss models and methods to explore the opportunities and address the challenges associated with pushing complex sensor processing tasks to the edge. Core themes of the presentation will include (1) model-based design methodologies, particularly those based on dataflow models of computation, for design and implementation of complex embedded hardware/software systems, and (2) design optimization techniques for efficiently utilizing multicore embedded processing platforms under stringent constraints on performance and energy consumption

Dr. Shuvra S. Bhattacharyya is a Professor in the Department of Electrical and Computer Engineering at the University of Maryland, College Park. He holds a joint appointment in the University of Maryland Institute for Advanced Computer Studies (UMIACS) and is affiliated with the Maryland Crime Research and Innovation Center (MCRIC). He also holds a part-time visiting position as Chair of Excellence in Design Methodologies and Tools at the National Institute for Applied Sciences (INSA) in Rennes, France. His research interests include signal processing, embedded systems, electronic design automation, machine learning, wireless communication, and wireless sensor networks. He received the Ph.D. degree from the University of California at Berkeley. He has held industrial positions as a Researcher at the Hitachi America Semiconductor Research Laboratory (San Jose, California), and Compiler Developer at Kuck & Associates (Champaign, Illinois). He is a Fellow of the IEEE and recipient of the NSF CAREER Award.

In this talk we will address the issue of building resilient systems in the face of cyberattacks. We will present defense mechanism for cyberattacks using a 3-tier architecture that can be used to secure army assets and tactical information. The top tier represents the front-end where autonomous sensing and inferencing through AI models take place by UAVs, UGVs, etc. We will illustrate how models can be defended against data poisoning attacks. In the middle tier we focus on building cyber defense against attacks in federated learning environments, where models are trained on large corpus of decentralized data without transferring raw over a communication channel. The bottom tier represents back-end servers that train deep learning models with large amounts of data that can subsequently be pushed to the edge for inferencing. We will demonstrate how adaptive models can be developed for detecting and preventing various types of attacks at this level.

Dr. Aryya Gangopadhyay is a Professor in the Information Systems department at the University of Maryland Baltimore County. Dr. Gangopadhyay has a courtesy appointment as a Professor in Computer Science and Electrical Engineering at UMBC. He is also the Director of the Center Realtime Sensing and Autonomy (CARDS) at UMBC. His research interests include adversarial machine learning at the edge, cybersecurity, and smart cities. He has graduated 16 PhD students and is currently mentoring several others at UMBC. He has published over 125 peer-reviewed research articles and has received extramural support from ARL, NSF, NIST, Department of Education, and IBM.

In today’s technology environment, information is abundant, dynamic, and heterogeneous in nature. Automated filtering and prioritization of information is based on the distinction between whether the information adds substantial value toward one’s goal or not. Contextual multi-armed bandit has been widely used for learning to filter contents and prioritize according to user interest or relevance. Learn-to-Rank technique optimizes the relevance ranking on items, allowing the contents to be selected accordingly. We propose a novel approach to top-K rankings under the contextual multi-armed bandit framework. We model the stochastic reward function with a neural network to allow non-linear approximation to learn the relationship between rewards and contexts. We demonstrate the approach and evaluate the performance of learning from the experiments using real world data sets in simulated scenarios. Empirical results show that this approach performs well under the complexity of a reward structure and high dimensional contextual features.

Dr. Jade Freeman is the Chief of the Battlefield Information Systems Branch, DEVCOM U.S. Army Research Laboratory (ARL), overseeing military information systems and analysis research projects. Prior to joining ARL, Dr. Freeman served as the Senior Statistician for the Chief of Staff at the Department of Homeland Security, Office of Cybersecurity and Communications, currently known as The Cybersecurity and Infrastructure Security Agency (CISA), Dr. Freeman obtained her Ph. D. in Statistics from George Washington University.