Talk Title: Ethomics - the AI-enabled way to understand human behaviour

Abstract : Here we present a novel AI-driven approach to human behaviour analytics called Ethomics (Kadirvelu et Faisal, 2023, Nature Medicine, Ricotti et Faisal, 2023, Nature Medicine) that allows unprecedented resolution in diagnosing and measuring disease progression. We apply the same AI framework to two very different degenerative diseases affecting adults (Friedreichs) and children (Duchenne). Crucially the AI method detects imperceptible changes to human behaviour that allows us to measure gene transcription rates from movement changes alone and can predict each individual patient’s disease trajectory up to a year into the future. Our ethomics technology allows us therefore to dramatically de-risk and accelerate drug development for rare diseases, as it allows us to cut the duration of clinical trials in half and requires only a fraction of patients to determine if a treatment is working compared to current „gold“-standard methods.

Talk Title: A Machine Learning Framework for Distributed Functional Compression over

Abstract : Deep Learning has revolutionized machine learning and has expanded its reach into many diverse fields, from autonomous driving to augmented reality and distributed IoT devices. Not unexpectedly, this has also led to deep- learning based design of communication systems. In particular, in all these applications, we often need to compute specific target functions that do not have any simple forms, e.g., obstacle detection, object recognition, etc. However, traditional cloud-based methods that focus on transferring data to a central location either for training or inference place enormous strain on wireless network resources. To address this, we develop a machine learning framework for distributed functional compression over wireless channels. We advocate that our machine learning framework can, by design, compute any arbitrary function for the desired functional compression task in IoT. In particular, the raw sensory data are never transferred to a central node for training or inference, thus reducing communication overhead. For these algorithms, we provide theoretical convergence guarantees and upper bounds on communication. Our simulations show that the learned encoders and decoders for functional compression perform significantly better than traditional approaches, are robust to channel condition changes and sensor outages. Compared to the cloud-based scenario, our algorithms reduce channel use by two orders of magnitude. Finally, we turn our attention to the problem of privacy in the distributed functional compression, where the node(s) are looking to hide private attributes correlated with the function value. We first study the single node and receiver problem. We then return to the distributed functional compression problem and devise a framework that demonstrates a state-of-the-art privacy-utility trade-off in the distributed scenario.

---

 

Yuejie Chi

       (Professor, Carnegie Mellon University)

Bio:

Dr. Yuejie Chi is a Professor in the department of Electrical and Computer Engineering, and a faculty affiliate with the Machine Learning department and CyLab at Carnegie Mellon University. She received her Ph.D. and M.A. from Princeton University, and B. Eng. (Hon.) from Tsinghua University, all in Electrical Engineering. Her research interests lie in the theoretical and algorithmic foundations of data science, signal processing, machine learning and inverse problems, with applications in sensing, imaging, decision making, and societal systems, broadly defined. Among others, Dr. Chi received the Presidential Early Career Award for Scientists and Engineers (PECASE) and the inaugural IEEE Signal Processing Society Early Career Technical Achievement Award for contributions to high-dimensional structured signal processing. She is an IEEE Fellow (Class of 2023) for contributions to statistical signal processing with low-dimensional structures.

Talk Title: Accelerating Ill-conditioned Low-rank Estimation via Scaled Gradient Descent

 

Abstract: Many problems encountered in science and engineering can be formulated as estimating a low-rank object from incomplete, and possibly corrupted, linear measurements; prominent examples include matrix completion and tensor completion. Through the lens of matrix and tensor factorization, one of the most popular approaches is to employ simple iterative algorithms such as gradient descent to recover the low-rank factors directly, which allow for small memory and computation footprints. However, the convergence rate of gradient descent depends linearly, and sometimes even quadratically, on the condition number of the low-rank object, and therefore, slows down painstakingly when the problem is ill-conditioned. This talk introduces a new algorithmic approach, dubbed scaled gradient descent (ScaledGD), that provably converges linearly at a constant rate independent of the condition number of the low-rank object, while maintaining the low per-iteration cost of gradient descent. A nonsmooth variant of ScaledGD provides further robustness to corruptions by optimizing the least absolute deviation loss. In addition, ScaledGD continues to admit fast global convergence, again almost independent of the condition number, from a small random initialization when the rank is over-specified. In total, ScaledGD highlights the power of appropriate preconditioning in accelerating nonconvex statistical estimation, where the iteration-varying preconditioners promote desirable invariance properties of the trajectory with respect to the symmetry in low-rank factorization.

---

                                                                                           

                                                                                                                                     

      Ehsan Afshari

                                        (Professor, University of Michigan)

Bio: Prof. Afshari received his Ph.D. EE from Caltech in 2006 and joined the ECE department of Cornell University. Ten years later, he joined the EECS department of the university of Michigan, Ann Arbor. His team is engaged in the theoretical foundations, design and experimental validation of analog, RF, mm-wave, and THz integrated devices, circuits and systems for a variety of applications including communications, imaging, and sensing. His work is funded by federal agencies such NSF, DARPA, ONR, and ARL as well as industry such as Intel, TI, Raytheon, and Qualcomm. He has been the recipient of several awards and honors, including a 2008 DARPA Young Faculty Award, a 2010 NSF CAREER Award, a first place at Stanford-Berkeley-Caltech Innovation Challenge in 2005, and several best paper awards at the leading conferences in his field. He has also served as a Distinguished Lecturer for the IEEE Solid-State Circuits Society. He is selected as one of 50 most distinguished alumni of Sharif University. His doctoral students have also received several prestigious awards and fellowships, including the 2018, 2017, 2012, 2011, and 2010 Solid-State Circuit Society Predoctoral Achievement Award, 2011, 2013, and 2017 IEEE MTT-S Microwave Engineering Graduate Fellowships, Cornell Best Ph.D. Thesis Award in 2011 and 2014, as well as many best paper awards. The Ph.D. graduates of his group are the leaders of the field including faculty members at MIT, UC Davis, UC Irvine, Penn State University, and University of Minnesota, and companies such as IBM, Bell Labs, Qualcomm and Broadcom.

---

Alexandre Bayen

(Professor, UC Berkeley)

Bio: Alexandre Bayen is the Associate Provost for Moffett Field Program Development at UC Berkeley, and the Liao-Cho Professor of Engineering at UC Berkeley. He is a Professor of Electrical Engineering and Computer Science(link is external), and Civil and Environmental Engineering(link is external). From 2014 - 2021, he served as the Director of the Institute of Transportation Studies(link is external) at UC Berkeley (ITS). He is also a Faculty Scientist in Mechanical Engineering, at the Lawrence Berkeley National Laboratory(link is external) (LBNL). He received the Engineering Degree in applied mathematics from the Ecole Polytechnique, France, in 1998, the M.S. and Ph.D. in aeronautics and astronautics from Stanford University in 1999 and 2004, respectively. He was a Visiting Researcher at NASA Ames Research Center from 2000 to 2003. Between January 2004 and December 2004, he worked as the Research Director of the Autonomous Navigation Laboratory at the Laboratoire de Recherches Balistiques et Aerodynamiques, (Ministere de la Defense, Vernon, France), where he holds the rank of Major. He has been on the faculty at UC Berkeley since 2005. Bayen has authored two books and over 200 articles in peer reviewed journals and conferences. He is the recipient of the Ballhaus Award from Stanford University, 2004, of the CAREER award from the National Science Foundation, 2009 and he is a NASA Top 10 Innovators on Water Sustainability, 2010. His projects Mobile Century and Mobile Millennium received the 2008 Best of ITS Award for ‘Best Innovative Practice’, at the ITS World Congress and a TRANNY Award from the California Transportation Foundation, 2009. Mobile Millennium has been featured more than 200 times in the media, including TV channels and radio stations (CBS, NBC, ABC, CNET, NPR, KGO, the BBC), and in the popular press (Wall Street Journal, Washington Post, LA Times). Bayen is the recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE) award from the White House, 2010. He is also the recipient of the Okawa Research Grant Award, the Ruberti Prize from the IEEE, and the Huber Prize from the ASCE.

Talk Title: Distributed AI Supercomputing: From Large-Scale Transformers to Graph Neural Networks

 

Abstract: Much of the astonishing progress in modern artificial intelligence is made by scaling to larger and larger deep learning models trained with more data. For example, the GPT-3 model with 175 billion parameters, trained with more than 500 billion tokens forms the basis for many services like Microsoft's Copilot and ChatGPT. We explain principles for training such large-scale models efficiently and how to design AI systems for this purpose. We then extend our discussion to emerging parallel and distributed Graph Neural Networks.