Reinforcement learning (RL), concerning decision making in uncertain environments, lies at the heart of modern artificial intelligence. Due to the high dimensionality, training of RL agents typically requires a significant amount of data to achieve desirable performance. However, data collection can be extremely time-consuming with limited access in real-world applications, especially when performed by a single agent. On the other hand, it is plausible to leverage multiple agents to collect data simultaneously, under the premise that they can learn a global policy collaboratively without the need of sharing local data in a federated manner. This talk provides a tour of recent advances in the non-asymptotic sample complexity of single-agent RL algorithms, and the fundamental statistical and communication trade-offs of federated RL algorithms, covering both blessings and curses that arises in long-horizon, robust, and heterogeneous settings.

Since July 2025, Yuejie Chi is the Charles C. and Dorothea S. Dilley Professor of Statistics and Data Science at Yale University, with a secondary appointment in Computer Science. She also spent some time as a visiting researcher at FAIR. Before joining Yale, she was the Sense of Wonder Group Endowed Professor of Electrical and Computer Engineering in AI Systems at Carnegie Melon University, with affiliation in MLD and CyLab. Her research interests lie in the theoretical and algorithmic foundations of data science, generative AI, reinforcement learning, and signal processing, motivated by applications in scientific and engineering domains. The problems her group studies are often interdisciplinary in nature, lying at the intersection of statistics, learning, optimization, and sensing. Her current focus is on improving the performance, efficiency and reliability of generative AI and decision making, driven by data-intensive but resource-constrained scenarios. Specific lines of research topics can be found here. She have been lucky to receive a couple of awards for her work, including Presidential Early Career Award for Scientists and Engineers (PECASE) from the White House. She is the inaugural recipient of the IEEE Signal Processing Society Early Career Technical Achievement Award for contributions to high-dimensional structured signal processing. In addition, she received SIAM Activity Group on Imaging Science Best Paper Prize, IEEE Signal Processing Society Young Author Best Paper Award, and young investigator awards from several agencies including NSF, ONR and AFOSR. She is an IEEE Fellow for contributions to statistical signal processing with low-dimensional structures. She was named the Goldsmith Lecturer by IEEE Information Theory Society in 2021, a Distinguished Lecturer by IEEE Signal Processing Society for 2022-2023, and a Distinguished Speaker by ACM for 2023-2026.

Unlike single-node ISAC, which is limited in robustness and environmental awareness, distributed ISAC (DISAC) networks exploit multi-node coordination--across base stations and user devices--to jointly deliver connectivity and multi-perspective sensing. The distributed aspect makes an entire re-design of fundamental transceiver functions necessary. For example, in a DISAC network, the precoder/combiner designs must be coordinated across multiple nodes in rapidly changing environments. In addition, hardware imperfections challenge coherence: antenna calibration scales to a complicated multi-dimensional problem, and multi-node synchronization in time, frequency and phase is challenging, but both aspects need to be addressed to achieve coherence. Distributed settings naturally lead to the challenge of jointly estimating the multiptah features associated with multiple user and target channels, which can later be exploited for communication, localization and sensing including imaging. This talk will present recent progress on algorithms and architectures for distributed transceivers that perform sensing, learning, and communication jointly--while remaining robust to hardware impairments, non-ideal propagation, and environmental dynamics.

Professor Nuria Gonzalez-Prelcic joined UC San Diego in 2024 as a Professor in the Department of Electrical and Computer Engineering. From 2020-2023, she was an Associate Professor in the Department of Electrical and Computer Engineering at North Carolina State University. From 2002-2020, she was an Associate Professor in the Department of Signal Theory and Communications at the University of Vigo, Spain. She completed her Ph.D. at the University of Vigo in Telecommunication Engineering. Professor Gonzalez-Prelcic has been developing signal processing theory and its applications ranging from topics such as wavelets and filterbanks to algorithms for advanced communications and sensing. Her group has made important contributions to millimeter wave MIMO communications. She pioneered the idea of sensor-aided wireless communications and joint communication and radar, which has blossomed into the topic of integrated sensing and communications. Her group developed the application of compressive sensing to estimate MIMO wireless communications channels using hybrid analog-digital beamforming architectures. Her work has been recognized by several awards. Her work on self-attention networks for user tracking received a best student paper award at the 2023 IEEE Signal Processing for Wireless Communications (SPAWC) conference. Her work on joint communication and radar was recognized with the 2022 IEEE Vehicular Technology Society Best Vehicular Electronics Paper Award. Her overview paper on signal processing for millimeter wave MIMO communications was recognized with the 2020 IEEE Signal Processing Society Donald G. Fink Overview Paper Award. She is a Distinguished Lecturer in the IEEE Vehicular Technology Society. She has led several academic centers or programs, many with significant industrial collaborations. She was the co-developer of 6GNC at NC State University, which involved eight companies. She was the Assistant Director of the UT SAVES (Situation-Aware Vehicular Engineering Systems) at UT Austin. She was the Founding Director, atlanTTic Research Center for Information and Communication Technologies, Vigo, Spain. This center involved around 75 faculty members with their PhD students and postdocs. She was the Director of the Research Cluster ''Competitiveness: technological progress and business management'', International Campus of Excellence Campus do Mar and the Developer and Founding Director of the Master's Program SIGMA ''Applications of Signal Processing in Communications'', University of Vigo. Prof. Gonzalez-Prelcic is involved with many efforts in the IEEE. She is an elected member of the IEEE Signal Processing Society Sensor, Array and Multichannel (SAM) Technical Committee (2017 - 2023), an elected member of the IEEE Signal Processing for Communications and Networking (SPCOM) Technical Committee (2021-present), an elected member of the IEEE Signal Processing Society Integrated Sensing and Communication Technical Working Group, (2021 - present), and a member of the IEEE Communications Society Integrated Sensing and Communication Emerging Technology Initiative (2021 - present). She was a member of the IEEE Signal Processing Society Education board (2022-2023). She is a Senior Member of the IEEE. She speaks English, Spanish, Galician and Portuguese.

One of the hallmarks of 6G is the ability of devices to jointly sense and communicate, as well as to provide ULLRC (ultra low latency reliable communication) links for time sensitive control and command signals. In this talk, we will focus on two applications in this area: radar for autonomous systems, and short packet blind communications. Compared to conventional radar, the challenges of autonomous driving radar include high dynamic range, low resolution, complex dynamic scenes with hundreds to thousands of targets, high false positive rates, and interference from other radars. In order to address these challenges, we will introduce an atomic norm minimization framework where the scene is assumed to consist of a collection of point targets (called atoms) and one attempts to find as succinct as possible an explanation for the received signal in terms of a linear superposition of atoms: hence Occam's radar. We show through extensive measurements that the approach achieves LiDAR-like performance and over 3X improvement in resolution per dimension, compared to conventional radar. Finally, we show that a family of signals used in radar are ideal for blind short packet communications. We thus introduce a new modulation scheme, MOCZ (modulation on conjugate zeros), that allows for communicating information over an unknown dispersive channel without the need to send pilot signals.

Babak Hassibi is the inaugural Mose and Lilian S. Bohn Professor of Electrical Engineering and Computing and Mathematical Sciences at the California Institute of Technology. His research interests span over various aspects of information theory, communications, signal processing, control, and machine learning. Among other awards, he is a recipient of the US Presidential Early Career Award for Scientists and Engineers (PECASE), the David and Lucille Packard Fellowship in Science and Engineering, and an honorary doctorate from Chalmers University, Sweden.

In recent years, new classes of structured and nonlinear random matrices have emerged in statistical estimation and machine learning. Understanding their spectral properties has become increasingly important, as these matrices are closely linked to key quantities such as the training and generalization performance of large neural networks and the fundamental limits of high-dimensional signal recovery. Unlike classical random matrix ensembles, these new matrices often involve nonlinear transformations, introducing additional structural dependencies that pose challenges for traditional analysis techniques. In this talk, I will present a set of equivalence principles that establish asymptotic connections between various nonlinear random matrix ensembles and simpler linear models that are more tractable for analysis. I will then demonstrate how these principles can be applied to characterize the performance of kernel methods and random feature models across different scaling regimes and to provide insights into the in-context learning capabilities of attention-based Transformer networks.

Yue M. Lu is a Harvard College Professor and Gordon McKay Professor of Electrical Engineering and Applied Mathematics at Harvard University. He has also held visiting appointments at Duke University (2016) and the Ecole Normale Superieure (ENS) in Paris (2019). His research focuses on the mathematical foundations of high-dimensional statistical estimation and learning. His contributions have been recognized with several best paper awards (IEEE ICIP, ICASSP, and GlobalSIP), the ECE Illinois Young Alumni Achievement Award (2015), and the IEEE Signal Processing Society Distinguished Lecturership (2022). He is a Fellow of the IEEE (Class of 2024).

The rapid proliferation of decentralized network architectures, such as mesh networks, has sparked growing interest in efficiently solving large-scale statistical learning tasks, especially when data is inherently distributed and lacks centralized oversight. Performing accurate statistical inference in such environments is a nontrivial task, particularly under stringent constraints on computational power, time, and inter-node communication. While statistical-computational trade-offs have been thoroughly characterized for high-dimensional inference in centralized settings, our understanding of these trade-offs within decentralized network environments remains comparatively limited. Indeed, methodologies that demonstrate robustness and accuracy in traditional low-dimensional contexts frequently underperform in high-dimensional regimes, and theoretical convergence results often fail to align with observed empirical behaviors. This divergence is largely attributable to the historical emphasis on optimization-centric design and analysis of decentralized algorithms, often overlooking critical statistical nuances. In this talk, we will introduce new algorithmic frameworks and analytical tools specifically tailored for decentralized high-dimensional inferential tasks. By integrating statistical insights into the design and analysis of decentralized optimization algorithms, we shed new light on existing gaps and misconceptions prevalent in the literature, thereby redefining our understanding of distributed inference methodologies.

Gesualdo Scutari is the Pedro and Granadillo Professor in the School of Industrial Engineering and Electrical and Computer Engineering at Purdue University, West Lafayette, IN, USA. His research interests focus on continuous optimization--particularly distributed and stochastic methods--equilibrium programming, and their applications in signal processing and statistical learning. Among others, he was a recipient of the 2013 NSF CAREER Award, the 2015 IEEE Signal Processing Society Young Author Best Paper Award, and the 2020 IEEE Signal Processing Society Best Paper Award. He served as an IEEE Signal Processing Distinguish Lecturer (2023-2024), and has been on the editorial broad of several IEEE journals. He is currently an Associate Editor for the SIAM Journal on Optimization. He is a Fellow of IEEE.

Consider an integrated sensing and communication (ISAC) system where a base station seeks to minimize the Cramer-Rao bound of a parameter estimation problem while satisfying quality-of-service constraints for communication users via spatial beamforming. How many simultaneous beamformers should be used? How to design these beamformers? We answer the former question by investigating rank-reduction strategies for the semidefinite programming relaxation solution and show that the minimum number of sensing beamformers scales at most linearly in the number of parameters to be estimated. Furthermore, we propose an optimization framework involving a transformation of the Cramer-Rao bound minimization problem into an equivalent max-min formulation and an extension of the uplink and downlink duality result for the classical multiuser MIMO communications problem into the ISAC setting. This results in a considerably more efficient iterative procedure for solving the optimal beamforming problem for ISAC than the semidefinite relaxation approach, while ensuring convergence to the global optimal solution.

Wei Yu received the B.A.Sc. degree in computer engineering and mathematics from the University of Waterloo, Canada, and the M.S. and Ph.D. degrees in electrical engineering from Stanford University, U.S.A. He is a Professor and Canada Research Chair in Information Theory and Wireless Communications in the Electrical and Computer Engineering Department at the University of Toronto in Canada. Prof. Wei Yu is a Fellow of IEEE and a Fellow of the Canadian Academy of Engineering. He was the recipient of the IEEE Marconi Prize Paper Award in Wireless Communications in 2019, the IEEE Communications Society Award for Advances in Communication in 2019, the IEEE Signal Processing Society Best Paper Award in 2008, 2017, and 2021, the IEEE Communications Society and Information Theory Society Joint Paper Award in 2024, and the R. A. Fessenden Award from IEEE Canada in 2024. Prof. Wei Yu is a Clarivate Highly Cited Researcher. He served as the President of the IEEE Information Theory Society in 2021.