AI Infrastructure: Foundations for Energy Efficiency and Scalability

Jon M. Huntsman Hall 3730 Walnut Street, Philadelphia, PA, United States

Click here for more details. The workshop will explore the state of the art in sustainable computing and share recent research at the intersection of technology, economics, and policy. Through invited talks, panel discussions, and breakout sessions, participants will help shape a research agenda for the field. The workshop aims to produce a white paper and publish […]

ESE Ph.D. Thesis Defense: ”Manifold Filters and Neural Networks: Geometric Graph Signal Processing in the Limit”

Amy Gutmann Hall, Room 515 3317 Chestnut Street, Philadelphia, United States

Graph Neural Networks (GNNs) are the tool of choice for scalable and stable learning in graph-structured data applications involving geometric information. My research addresses the fundamental questions of how GNNs can generalize across different graph scales and how they can remain stable on large-scale graphs. I do so by considering manifolds as graph limit models. […]

ESE Ph.D. Thesis Defense: “Training Adaptive and Sample-Efficient Autonomous Agents”

Room 512, Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

AI agents, both in the physical and digital worlds, should generalize from their training data to three increasingly difficult levels of deployment: training tasks and environments, training tasks and environments with variations, and completely new tasks and environments. Moreover, like humans, they are expected to learn from as little training data as possible, especially in […]

IDEAS/STAT Optimization Seminar: Resilient Distributed Optimization for Cyberphysical Systems

Amy Gutmann Hall, Room 414 3333 Chestnut Street, Philadelphia, United States

Zoom link: https://upenn.zoom.us/j/98220304722   Abstract: This talk considers the problem of resilient distributed multi-agent optimization for cyberphysical systems in the presence of malicious or non-cooperative agents. It is assumed that stochastic values of trust between agents are available which allows agents to learn their trustworthy neighbors simultaneously with performing updates to minimize their own local […]

ESE Ph.D. Thesis Defense: “Neural Compression: Estimating and Achieving the Fundamental Limits”

Amy Gutmann Hall, Room 515 3317 Chestnut Street, Philadelphia, United States

Neural compression, which pertains to compression schemes that are learned from data using neural networks, has emerged as a powerful approach for compressing real-world data. Neural compressors often outperform classical schemes, especially in settings where reconstructions that are perceptually similar to the source are desired. Despite their empirical success, the fundamental principles governing how neural […]

ESE Ph.D. Thesis Defense: “Machine Learning for Large-Scale Cyber-Physical Systems”

Raisler Lounge (Room 225), Towne Building 220 South 33rd Street, Philadelphia, PA, United States

Directly training deep learning models for applications in large-scale cyber-physical systems can be intractable due to the large number of components and decision variables. Instead, we focus on exploiting spatial symmetries in systems by designing size-generalizable architectures. Once trained on small-scale examples, such architectures exhibit equivalent or comparable performance on large-scale systems. The first example […]

ESE 5160 Special Lecture: “Taking RoboRacer Off-Road: Learning Extreme Off-Road Mobility”

Towne 327

In this guest lecture, we will cover two recent research thrusts from the RobotiXX lab in taking RoboRacer off-road: high-speed off-road navigation and wheeled mobility on vertically challenging terrain. For high-speed off-road navigation, we will introduce a sequential line of work with every work inspired by and built upon its prior work, ranging from inverse […]

ESE Ph.D. Thesis Defense: “Inverse design for engineering complex light-matter interaction”

Moore 317 200 S 33rd Street, Philadelphia, PA, United States

The inverse design paradigm has emerged as a transformative approach for the synthesis of nanophotonic structures, offering a powerful alternative to conventional intuition-driven design. By approaching photonic device design as a computational optimization problem, inverse design enables the systematic exploration of high-dimensional parameter spaces to uncover non- intuitive structures that meet complex performance targets. This […]

ESE Ph.D. Thesis Defense: “Graph Neural Networks for Communication in Multi-Agent Systems”

Room 313, Singh Center for Nanotechnology 3205 Walnut Street, Philadelphia, PA, United States

Communication networks support a wide range of applications in multi-agent systems by solving core problems such as routing, scheduling, and resource allocation. In this thesis, we focus on data-driven routing and scheduling strategies using local information subject to constraints using Graph Neural Networks (GNNs). First, we study information routing in communication networks with constant channel […]

ESE Guest Seminar – “Efficient Computing for AI and Robotics: From Hardware Accelerators to Algorithm Design”

Raisler Lounge (Room 225), Towne Building 220 South 33rd Street, Philadelphia, PA, United States

The compute demands of AI and robotics continue to rise due to the rapidly growing volume of data to be processed; the increasingly complex algorithms for higher quality of results; and the demands for energy efficiency and real-time performance. In this talk, we will discuss the design of efficient tailored hardware accelerators and the co-design […]