Select a calendar:
Filter February Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for February
-
PhD Thesis Proposal - Matthew Ferland
Thu, Feb 01, 2024 @ 12:30 AM - 02:00 PM
Thomas Lord Department of Computer Science
University Calendar
Event: PhD Thesis Proposal (Matthew Ferland)
Committee: Shanghua Teng, David Kempe, Jiapeng Zhang, Shaddin Dughmi, and Larry Goldstein
Date: February 1, 2024, 12:30pm – 2:00pm
Title: Exploring the complexity landscape of combinatorial games
Abstract: People have been playing games since before written history, and many of the earliest games were combinatorial games, that is to say, games of perfect information and no chance. This type of game is still widely played today, and many popular games of this type, such as Chess and Go, are some of the most studied games of all time. This proposed work resolves around a game-independent systemic study of these games, involving computational properties involving evaluating the mathematical analysis tools, such as sprague-grundy values and switches, as well identifying what can be determined about these games under simple oracle models.
Location: Henry Salvatori Computer Science Center (SAL) - 213
Audiences: Everyone Is Invited
Contact: CS Events
-
PhD Defense - KR Zentner
Thu, Feb 01, 2024 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Leveraging Cross-Task Transfer in Sequential Decision Problems: Scalable Reinforcement Learning for Robotics
Defense Committee: Gaurav Sukhatme (chair), Heather Culbertson, Stefanos Nikolaidis, Laurent Itti, Bhaskar Krishnamachari
Date: Feb 1, 2024, 2 p.m. - 4 p.m. - RTH 217
Abstract: The past few years have seen an explosion of interest in using machine learning to make robots capable of learning a diverse set of tasks. Potentially, these robots could operate in close proximity to humans, assisting humans with a wide variety of needs and being instructed to perform new tasks as needed. However, these robots generally use Reinforcement Learning to learn detailed sub-second interactions, but consequently require large amounts of data for each task. In this thesis we explore how Reinforcement Learning can be combined with Transfer Learning to re-use data across tasks. We begin by reviewing the state of Multi-Task and Meta RL and describe the motivations for using Transfer Learning. Then, we describe a basic framework for using Transfer Learning to efficiently learn multiple tasks, and show how it requires predicting how effectively transfer can be performed across tasks. Next, we present a simple rule, based in information theory, for predicting the effectiveness of Cross-Task Transfer, which we call the "Transfer Cost Rule." We discuss the theoretical implications of that rule, and show various quantitative evaluations of it. Then, we show two directions of work making use of our insights to perform efficient Transfer Reinforcement Learning. The first of these directions uses Cross-Task Co-Learning and Plan Conditioned Behavioral Cloning to share skill representations produced by a Large Language Model, and is able to learn many tasks from a single demonstration each in a simulated environment. The second of these directions uses Two-Phase KL Penalization to enforce a (potentially off-policy) trust region. These advances in Transfer RL may enable robots to be used in a wider range of applications, such as in the home or office. The insight provided by the Transfer Cost Rule may also be relevant to a wide audience of Reinforcement Learning practitioners, since it provides a practical and theoretically grounded explanation for the performance of Deep Reinforcement Learning algorithms.
Zoom link: https://usc.zoom.us/j/96965616504?pwd=QngwQTJsTXJkbXJJNU9hRVV2Mk1DQT09Location: Ronald Tutor Hall of Engineering (RTH) - 217
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/96965616504?pwd=QngwQTJsTXJkbXJJNU9hRVV2Mk1DQT09
-
PhD Thesis Proposal - Hsien-Te Kao
Fri, Feb 02, 2024 @ 01:00 PM - 02:30 PM
Thomas Lord Department of Computer Science
University Calendar
Committee: Emilio Ferrara (Chair), Kristina Lerman, Phebe Vayanos, Souti Chattopadhyay, Ruishan Liu
Date and Time: Friday, February 2, 2024, 1:00 PM - 2:30 PM PST - RTH 115
Title: Cold Start Prediction in Personalized mHealth
Abstract: Mobile health has brought fundamental changes to the healthcare industry, offering new hope in addressing growing healthcare expenditures, opportunity costs, and labor shortages. Machine learning is driving mobile health towards decentralized healthcare by automating health monitoring, diagnosis, and treatment. Personalized mobile health systems are a key component in advancing patient-centric healthcare, but these systems remain unfeasible outside of hospital settings because personal health data is largely inaccessible, uncollectible, and regulated. In this proposal, we introduce a personalized mobile health system to predict individual health status without user context through a set of mobile, wearable, and ubiquitous technologies. The model leverages collaborative filtering to replace missing user context with learned similar group characteristics, where user similarity is captured through multiple dimensions of cognitive appraisal based on a combination of psychology theories. The system eliminates user dependence through passive feedback that satisfies real-world constraints. Our preliminary results demonstrate a proof-of-concept system.Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: CS Events
-
PhD Thesis Proposal - Ayush Jain
Mon, Feb 05, 2024 @ 04:00 PM - 06:00 PM
Thomas Lord Department of Computer Science
University Calendar
Thesis Proposal: Ayush Jain
Date: February 5, 2024 (Monday), 4 pm - 6 pm
Location: TBD
Committee: Erdem Biyik, Joseph J Lim, Gaurav Sukhatme, Stefanos Nikolaidis, Fefei Qian
Title: Enabling Robust Reinforcement Learning in Challenging Action Spaces
Abstract: The action space of an agent defines its interface to interact with the world. It can take two forms: discrete, as in recommender systems making decisions from millions of choices, or continuous, as in robots actuating control movements. While humans excel at a vast range of action spaces, from deciding between potentially unseen choices to making precise dexterous control like in surgery, conventional reinforcement learning (RL) is limited to simple action spaces beyond which agents fail entirely. Concretely, discrete RL typically assumes a "static" action space that never changes, while continuous RL assumes a "smooth" action space such that nearby actions have similar consequences. My goal is to alleviate these assumptions to broaden the applicability of RL agents to tasks with challenging action spaces. Thus, I build discrete RL algorithms that can adapt to any available action set and even choose from actions never seen before, such as recommending new items and choosing from unseen toolsets. In continuous action space tasks like robotics, I show how conventional agents get stuck on suboptimal actions due to a challenging action space. To address this, I propose a novel actor-critic algorithm enabling actors to search for more optimal actions.
Location: TBD
Audiences: Everyone Is Invited
Contact: CS Events
-
CS Colloquium - Nathan Sturtevant (University of Alberta / Amii) - Researching the foundations of heuristic search
Wed, Feb 07, 2024 @ 09:00 AM - 10:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nathan Sturtevant, University of Alberta / Amii
Talk Title: Researching the foundations of heuristic search
Abstract: Although the field of heuristic search is over 50 years old, the last 6-7 years have seen numerous revisions to the foundational algorithms in the field. These include the theories for bidirectional search, for suboptimal search, and for improving the worst-case performance of fundamental algorithms such as A* and IDA*. This talk will give an overview of these new results, demonstrating the changes and their impact, many of which center around the notion of whether re-expansions are allowed during search.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Nathan is a Fellow and Canada CIFAR AI Chair at Amii and a Professor in the Department of Computing Science at the University of Alberta. His research looks broadly at heuristic and combinatorial search problems, including both theoretical and applied approaches, with many applications in games. His work on pathfinding was used in the game Dragon Age: Origins, and will appear in the upcoming Nightingale. Nathan’s work has won the best paper awards at the AAAI, and SoCS conferences, as well as the AI Journal Prominent Paper Award.
Host: Sven Koenig
More Info: https://usc.zoom.us/j/6192383533
Location: https://usc.zoom.us/j/6192383533
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/6192383533
-
CS Colloquium - Chien-Ming Huang (Johns Hopkins University) - Becoming Teammates: Designing Assistive, Collaborative Machines
Wed, Feb 07, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Chien-Ming Huang , Johns Hopkins University
Talk Title: Becoming Teammates: Designing Assistive, Collaborative Machines
Abstract: The growing power in computing and AI promises a near-term future of human-machine teamwork. In this talk, I will present my research group’s efforts in understanding the complex dynamics of human-machine interaction and designing intelligent machines aimed to assist and collaborate with people. I will focus on 1) tools for onboarding machine teammates and authoring machine assistance, 2) methods for detecting, and broadly managing, errors in collaboration, and 3) building blocks of knowledge needed to enable ad hoc human-machine teamwork. I will also highlight our recent work on designing assistive, collaborative machines to support older adults aging in place.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Chien-Ming Huang is the John C. Malone Assistant Professor in the Department of Computer Science at the Johns Hopkins University. His research focuses on designing interactive AI aimed to assist and collaborate with people. He publishes in top-tier venues in HRI, HCI, and robotics including Science Robotics, HRI, CHI, and CSCW. His research has received media coverage from MIT Technology Review, Tech Insider, and Science Nation. Huang completed his postdoctoral training at Yale University and received his Ph.D. in Computer Science at the University of Wisconsin–Madison. He is a recipient of the NSF CAREER award. https://www.cs.jhu.edu/~cmhuang/
Host: Stefanos Nikolaidis
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Events
-
PhD Thesis Defense - Sepanta Zeighami
Wed, Feb 07, 2024 @ 01:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
Committee members: Cyrus Shahabi (chair), Keith Chugg, Vatsal Sharan, Haipeng Luo
Title: A Function Approximation View of Database Operations for Efficient, Accurate, Privacy-Preserving & Robust Query Answering with Theoretical Guarantees
Abstract: Machine learning models have been recently used to replace various database components (e.g., index, cardinality estimator) and provide substantial performance enhancements over their non-learned alternatives. Such approaches take a function approximation view of the database operations. They consider the database operation as a function that can be approximated (e.g., an index is a function that maps items to their location in a sorted array) and learn a model to approximate the operation's output. In this thesis, we first develop the Neural Database (NeuroDB) framework which extends this function approximation view by considering the entire database system as a function that can be approximated. We show, utilizing this framework, that training neural networks that take queries as input and are trained to output query answer estimates provide substantial performance benefits in various important database problems including approximate query processing, privacy-preserving query answering, and query answering on incomplete datasets. Moreover, we present the first theoretical study of this function approximation view of database operations, providing the first-ever theoretical analysis of various learned database operations. Our analysis provides theoretical guarantees on the performance of the learned models, showing why and when they perform well. Furthermore, we theoretically study the model size requirements, showing how model size needs to change as the dataset changes to ensure a desired accuracy level. Our results enhance our understanding of learned database operations and provide the much-needed theoretical guarantees on their performance for robust practical deployment.
Zoom Link: https://usc.zoom.us/j/91683810479?pwd=VXBmblhDdzZCZU1Oc05jRFV2dzI2dz09
Meeting ID: 916 8381 0479
Passcode: 250069Location: Charles Lee Powell Hall (PHE) - 106
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/91683810479?pwd=VXBmblhDdzZCZU1Oc05jRFV2dzI2dz09
-
CCI, AAI, and MHI Joint Seminar Series - Radoslav Ivanov (Rensselaer Polytechnic Institute): Safe and secure autonomy within reach: a verified machine learning and control perspective
Tue, Feb 13, 2024 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Radoslav Ivanov, Rensselaer Polytechnic Institute
Talk Title: Safe and secure autonomy within reach: a verified machine learning and control perspective
Abstract: In this talk, I will present an integrated approach to assuring the safety and security of cyber-physical systems (CPS) through a combination of offline verification and online monitoring techniques. For offline assurance, I have developed an approach, called Verisig, for verifying the safety of autonomous systems with neural network controllers. I will present an exhaustive evaluation on a neural-network-controlled (1/10-scale) autonomous racing car, in terms of modeling, verification and experiments on the real platform. In the second part of the talk, I will describe my work on run-time monitoring of system safety, with applications to medical CPS. Specifically, I will present a detector for critical drops in the patient's oxygen content during surgery, with guaranteed performance regardless of varying physiological parameters such as metabolism. The detector is evaluated on real-patient data collected from the Children's Hospital of Philadelphia.
Zoom Link: https://usc.zoom.us/j/98624281836?pwd=ajJSWGRvbkRpUVgvRC9nOXd5K29TZz09 Meeting ID: 986 2428 1836 Passcode: CPS24
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Radoslav Ivanov He is an Assistant Professor in Computer Science at the Rensselaer Polytechnic Institute. Prior to that, he was a postdoc at the PRECISE center at the University of Pennsylvania. Radoslav received the B.A. degree in computer science and economics from Colgate University in 2011, and the Ph.D. degree in computer and information science from the University of Pennsylvania in 2017. His research interests are broadly in the field of safe and secure autonomy, with a focus on verified machine learning, control theory and cyber-physical security. The natural application domains of his work are automotive and medical cyber-physical systems.
Host: Pierluigi Nuzzo and Lars Lindemann
More Info: https://usc.zoom.us/j/98624281836?pwd=ajJSWGRvbkRpUVgvRC9nOXd5K29TZz09
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/98624281836?pwd=ajJSWGRvbkRpUVgvRC9nOXd5K29TZz09
-
Computer Science General Faculty Meeting
Wed, Feb 14, 2024 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Ass
-
CS Colloquium: Parastoo Abtahi (Princeton University) - From Haptic Illusions to Beyond Real Interactions in Virtual Reality
Wed, Feb 14, 2024 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Parastoo Abtahi, Princeton University
Talk Title: From Haptic Illusions to Beyond Real Interactions in Virtual Reality
Abstract: Advances in audiovisual rendering have led to the commercialization of virtual reality (VR) hardware; however, haptic technology has not kept up with these advances. While haptic devices aim to bridge this gap by simulating the sensation of touch, many hardware limitations make realistic touch interactions in VR challenging. In my research, I explore how by understanding human perception, we can design VR interactions that not only overcome the current limitations of VR hardware but also extend our abilities beyond what is possible in the real world. In this talk, I will present my work on redirection illusions that leverage the limits of human perception to improve the perceived performance of encountered-type haptic devices, such as improving the position accuracy of drones, the speed of tabletop robots, and the resolution of shape displays when used for haptics in VR. I will then present a framework I have developed through the lens of sensorimotor control theory to argue for the exploration and evaluation of VR interactions that go beyond mimicking reality.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Parastoo Abtahi is an Assistant Professor of Computer Science at Princeton University, where she leads Princeton’s Situated Interactions Lab (Ψ Lab) as part of the Princeton HCI Group. Before joining Princeton, Parastoo was a visiting research scientist at Meta Reality Labs Research. She received her PhD in Computer Science from Stanford University, working with Prof. James Landay and Prof. Sean Follmer. Her research area is human-computer interaction, and she works broadly on augmented reality and spatial computing. Parastoo received her bachelor’s degree in Electrical and Computer Engineering from the University of Toronto, as part of the Engineering Science program
Host: Heather Culbertson
More Info: https://usc.zoom.us/j/95030499252?pwd=YVl3dU93ZUlTeVNrWEFVeWNkYjB2Zz09
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: CS Events
Event Link: https://usc.zoom.us/j/95030499252?pwd=YVl3dU93ZUlTeVNrWEFVeWNkYjB2Zz09
-
PhD Thesis Proposal - Saghar Talebipour
Tue, Feb 20, 2024 @ 01:30 AM - 03:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Saghar Talebipour
Committee Members: Nenad Medvidovic (Chair), William G.J. Halfond, Chao Wang, Mukund Raghothaman, Sandeep Gupta
Date: Tuesday, February 20, 2024, 1:30 p.m. - 3:00 p.m. Location: EEB 349
Title: Automated Usage-based Mobile Application Testing via Artifact Reuse
Abstract: Writing and maintaining UI tests for mobile applications is both time-consuming and tedious. While decades of research have led to automated methods for UI test generation, these methods have largely focused on identifying crashes or maximizing code coverage. However, recent studies have emphasized the significance of usage-based tests targeting specific app functionalities and use cases. My research introduces novel automated testing techniques that make use of existing artifacts, such as tests from similar applications or video recordings of app operations. These approaches help us move closer to achieving the goal of automated usage-based testing of mobile applications.Location: Hughes Aircraft Electrical Engineering Center (EEB) - 349
Audiences: Everyone Is Invited
Contact: CS Events
-
CS Colloquium - Krishna Kant Chintalapudi (Microsoft Research Redmond) - "Leveling up Next Gen Xbox User Experience with Neural Networks and Sound"
Tue, Feb 20, 2024 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Krishna Kant Chintalapudi, Principal Researcher, Microsoft Research Redmond (MSR)
Talk Title: Leveling up Next Gen Xbox User Experience with Neural Networks and Sound
Abstract: This talk presents two groundbreaking innovations in enhancing the gaming experience on Next-Gen Xbox platforms - ADR-X (NSDI 2024) and Ekho (SIGCOMM 2023). ADR-X, is a neural network-assisted wireless link rate adaptation technique for compute-constrained embedded gaming devices. It uses a meticulously crafted NN based contextual bandit that leverages existing communication theory domain knowledge. This allows ADR-X to perform at par with state-of-the-art reinforcement learning techniques such as PPO while also running 100× faster. Ekho introduces a novel approach to synchronizing cloud gaming media over the internet - crucial for immersive gameplay. By embedding faint, human-inaudible pseudo-noise markers into game audio and detecting them through player microphones, Ekho accurately measures and compensates for inter-stream delays.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Krishna Kant Chintalapudi is a Principal Researcher in the Networking Research Group at Microsoft Research Redmond (MSR). His research interests span AI/ML, Networking & Systems, Video Analytics, AR/VR and Internet of Things. He has published more than 50 papers in reputed international conferences and journals which have been cited over 8000 times and he holds over 30 patents granted by USPTO. Krishna graduated from the University of Southern California with a Phd in Computer Science in 2006. Prior to joining MSR, Krishna was a Senior Research Engineer at Bosch Research and Technology Center in Palo Alto, CA, USA.
Host: Ramesh Govindan
Location: Hedco Neurosciences Building (HNB) - 107
Audiences: Everyone Is Invited
Contact: CS Events
-
CS Colloquium - Pavithra Prabhakar (Kansas State University) - Safety Analysis of AI-enabled Cyber-Physical Systems (CPS): A Formal Approach
Tue, Feb 20, 2024 @ 02:00 PM - 03:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Prof. Pavithra Prabhakar, Kansas State University
Talk Title: Safety Analysis of AI-enabled Cyber-Physical Systems (CPS): A Formal Approach
Abstract: AI-based components have become an integral part of Cyber-Physical Systems enabling transformative functionalities. With the ubiquitous use of Machine Learning components in perception, control and decision making in safety critical application domains such as automotive and aerospace, rigorous analysis of these systems has become imperative toward real-world deployment. In this talk, we will present a formal approach to verifying the safety of AI-enabled CPS. We consider a closed-loop system consisting of a dynamical system model of the physical plant and a neural network model of the perception/control modules and analyze the safety of this system through reachable set computation.
One of the main challenges with reachable set computation of neural network-controlled CPS is the scalability of the methods to large networks and complex dynamics. We present a novel abstraction technique for neural network size reduction that provides soundness guarantees for safety analysis and indicates a promising direction for scalable analysis of the closed-loop system. Specifically, our abstraction consists of constructing a simpler neural network with fewer neurons, albeit with interval weights called interval neural network (INN), which over-approximates the output range of the given neural network. We present two methods for computing the output range analysis problem on the INNs, one by reducing it to solving a mixed integer linear programming problem, and the other a symbolic computation method using a novel data structure called the interval star set. Our experimental results highlight the trade-off between the computation time and the precision of the computed output set. We will discuss other foundational questions on neural network size reduction by exploring the notion of equivalence and approximate equivalence. We will conclude by pointing to ongoing work on incorporating a camera model along with a neural network for perception in the closed-loop system framework.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Pavithra Prabhakar is professor in the department of computer science, and the Peggy and Gary Edwards Chair in Engineering at Kansas State University. She is currently serving the National Science Foundation as a Program Director in the Software and Hardware Foundations Cluster in the Computer and Information Science and Engineering Directorate, where she manages formal methods and verification portfolio. Specifically, she leads the Formal Methods in the Field (FMitF) program, has been a founding program director for the Safe Learning Enabled Systems (SLES) program and is a cognizant program director for the Foundations of Robotics Research (FRR) and the Cyber-Physical Systems (CPS) program.
She obtained her doctorate in computer science and a master's degree in applied mathematics from the University of Illinois at Urbana-Champaign, followed by a CMI postdoctoral fellowship at the California Institute of Technology. Prior to coming to K-State, she spent four years at the IMDEA Software Institute in Spain as a tenure-track assistant professor. She is the recipient of a Marie Curie Career Integration Grant from the European Union (2014), an NSF CAREER Award (2016), an ONR Young Investigator Award (2017), NITW distinguished young alumnus award (2021), and an Amazon Research Award (2022).
Host: Jyotirmoy Deshmukh
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: CS Events
-
PhD Thesis Proposal - Qinyi Luo
Wed, Feb 21, 2024 @ 11:00 AM - 12:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Qinyi Luo
Title: High-Performance Heterogeneity-Aware Distributed Machine Learning Model Training
Committee members: Xuehai Qian (co-chair), Viktor Prasanna (co-chair), Ramesh Govindan, Chao Wang, Salman Avestimehr
Abstract: The increasing size of machine learning models and the ever-growing amount of data result in days or even weeks of time required to train a machine learning model. To accelerate training, distributed training with parallel stochastic gradient descent is widely adopted as the go-to training method. This thesis proposal targets four challenges in distributed training: (1) performance degradation caused by large amount of data transfer among parallel workers, (2) heterogeneous computation and communication capacities in the training devices, i.e., the straggler problem, (3) huge memory consumption during training caused by huge model sizes, and (4) automatic selection of parallelization strategies. The proposal first introduces our work in decentralized training, including system support and algorithmic innovation that strengthen tolerance against stragglers in data-parallel training. Then, an adaptive during-training model compression technique is proposed to reduce the memory consumption of training huge recommender models. In the end, in the aspect of automatic parallelization of training workloads, a novel unified representation of parallelization strategies is proposed, as well as a search algorithm that selects superior parallel settings in the vast search space, and preliminary findings are discussed.
Date and time: Feb 21 11am-12:30pm
Location: EEB 110
Zoom link: https://usc.zoom.us/j/97299158202?pwd=bVlnRVFhTjJlZjVCY1hVNy9yWWE1UT09Location: Hughes Aircraft Electrical Engineering Center (EEB) - 110
Audiences: Everyone Is Invited
Contact: CS Events
-
Center of Autonomy and AI, Center for Cyber-Physical Systems and the Internet of Things, and Ming Hsieh Institute for Electrical & Computer Engineering Joint Seminar Series: Dengwang Tang (USC)
Thu, Feb 22, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dengwang Tang, University of Southern California
Talk Title: Informed Posterior Sampling Based Algorithms for Markov Decision Processes
Series: Center of Autonomy and AI, Center for Cyber-Physical Systems and the Internet of Things, and Ming Hsieh Institute for Electrical & Computer Engineering Joint Seminar Series
Abstract: The traditional paradigm of RL often features an agent who learns to control the system only through interaction. However, such a paradigm can be impractical since
learning can be very slow. In many engineering applications, there's often an offline dataset available before the application of the online learning algorithm. We proposed
the informed posterior sampling-based reinforcement learning (iPSRL) to use offline datasets to bootstrap online RL algorithms in both episodic and continuing MDP
learning problems. In this algorithm, the learning agent forms an informed prior with the offline data along with the knowledge about the offline policy that generated the data.
This informed prior is then used to initiate the posterior sampling procedure. Through a novel prior-dependent regret analysis of the posterior sampling procedure, we showed
that when the offline data is informative enough, the iPSRL algorithm can significantly reduce the learning regret compared to the baseline. Based on iPSRL, we then
proposed the more practical iRLSVI algorithm and we showed that in episodic MDP learning problems, it can significantly reduce regret via empirical results.
Biography: Dengwang Tang is currently a postdoctoral researcher at University of Southern California. He obtained his B.S.E in Computer Engineering from University of Michigan,
Ann Arbor in 2016. He earned his Ph.D. in Electrical and Computer Engineering (2021), M.S. in Mathematics (2021), and M.S. in Electrical and Computer Engineering (2018) all
from University of Michigan, Ann Arbor. Before joining USC, he was a postdoctoral researcher at University of California, Berkeley. His research interests involve control
and learning algorithms in stochastic dynamic systems, multi-agent systems, queuing theory, and dynamic games.
Host: Pierluigi Nuzzo
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: CS Events
-
CS Colloquium: Luyi Xing (Indiana University) - Security Foundations for Cloud-based IoT Systems
Wed, Feb 28, 2024 @ 10:00 AM - 11:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Luyi Xing, Indiana University
Talk Title: Security Foundations for Cloud-based IoT Systems
Abstract: The Internet of Things (IoT) cloud is one of the key pillars of the foundation upon which modern IoT systems rest (Smart Home, Industrial, Smart City, Retail, and Health applications, etc.). IoT manufacturers generally deploy IoT devices under managed PaaS and IaaS IoT cloud services (e.g., AWS IoT Core, Azure IoT Hub, SmartThings, Apple Home/iCloud), which offload much of the security responsibilities and deployment burden to the cloud providers. IoT clouds must trust-manage hundreds of millions of IoT devices and users, and provide device manufacturers reliable and usable tools for secure IoT deployments and control. In IoT systems, compromised security or improper deployments can cause hazardous situations and serious consequences. In this talk, we will focus on three areas of fundamental problems in the security of IoT systems: (1) IoT supply chain, (2) IoT security models and real-world deployments, (3) emerging IoT design and application paradigms. Our systematic research in advancing these areas are backed by formal verification, automatic analysis on protocols and programs, and ML/AI-based semantic analysis and formal-model generation. We developed principled, open-source approaches to reveal emerging threats, and formally verify complex, deployed IoT systems to provide new security and privacy guarantees. We identified more than 50 new types of attacks/vulnerabilities in 200+ IoT devices/services (e.g., smart locks, drones) with serious security, safety, and privacy implications. Our formal verification tools have been adopted by industry and government agencies such as AWS. Our security patches have been adopted and deployed by 50+ IoT vendors (AWS IoT, Apple HomeKit, Samsung SmartThings, Microsoft Azure IoT, Yale Locks, August, iRobot, etc.).
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Luyi Xing is an Assistant Professor in the department of Computer Science, Luddy School of Informatics, Computing, and Engineering at Indiana University Bloomington since 2018. He is founder of the System Security Foundations lab at IU. Prior to IU, he had years of professional experience in engineering large production systems at AWS and Amazon. He is a recipient of the NSF CAREER award (2021, IoT systems security), Facebook Research Award (2021, Privacy Enhancing Technologies), 5 Facebook Whitehat awards (2012, 2013, 2020, 2021), Google Developer Data Protection award (2019), Microsoft Whitehat award (2019), Android Security Acknowledgements (2013 - 2016, 2018) and Apple Security Acknowledgement (2015, 2019, 2020), among others. His research has changed the design space (access control, authentication) of hundreds of operating system modules (Unix/Linux based OSes, MacOS, Android, iOS), applications, and online services that almost every citizen uses every day. His research aims at improving guarantees for security and privacy in deployed systems, in particular, IoT, cloud, mobile, and software supply chain, with efforts in formal verification, program analysis, machine learning/NLP, compliance, and technology standardization. His research has led to the discovery of 100+ new types of vulnerabilities in the design of commercial and open-source systems, uncovering new attack techniques and undermining prior security guarantees and assumptions. He is a pioneer for a few key research directions, including formal methods for IoT systems security, logic flaws in systems, iOS security and privacy, and security of IoT standards. He is an active practitioner in applying AI/NLP for system security and formal methods.
Host: Chao Wang
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: CS Faculty Affairs
-
Computer Science General Faculty Meeting
Wed, Feb 28, 2024 @ 12:00 PM - 02:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Assistant to CS Chair
