— Day 1: Online Scalable Learning Adaptive to Unknown Dynamics and Graphs – Part I: Multi-kernel Approaches
curse of dimensionalityassociated with kernel methods. We will also present an adaptive multi-kernel learning scheme (termed AdaRaker) that relies on weighted combinations of advices from hierarchical ensembles of experts to boost performance in dynamic environments. The weights account not only for each kernel’s contribution to the learning process, but also for the unknown dynamics. Performance is analyzed in terms of both static and dynamic regrets. AdaRaker is uniquely capable of tracking nonlinear learning functions in environments with unknown dynamics, with analytic performance guarantees. The approach is further tailored for online graph-adaptive learning with scalability and privacy. Tests with synthetic and real datasets will showcase the effectiveness of the novel algorithms.
— Day 2: Online Scalable Learning with Adaptivity and Robustness – Part II: Deep and Ensemble GPs
Prof. Georgios B. Giannakis, ADC Chair in Wireless Telecommunications and McKnight Presidential Chair in ECE, University of Minnesota. Georgios B. Giannakis (Fellow’97) received his Diploma in Electrical Engr. (EE) from the Ntl. Tech. Univ. of Athens, Greece, 1981. From 1982 to 1986 he was with the U. of Southern California (USC), where he received his MSc. in EE, 1983, MSc. in Mathematics, 1986, and Ph.D. in EE, 1986. He was with the U. of Virginia from 1987 to 1998, and since 1999 he has been with the U. of Minnesota, where he holds a Chair in Wireless Communications, a U. of Minnesota McKnight Presidential Chair in ECE, and serves as director of the Digital Technology Center. His general interests span the areas of statistical learning, communications, and networking - subjects on which he has published more than 460 journal papers, 760 conference papers, 26 book chapters, two edited books and two research monographs. Current research focuses on Data Science with applications to brain, and power networks with renewables. He is the (co-) inventor of 33 patents issued, and the (co-) recipient of 9 best journal paper awards from the IEEE Signal Processing (SP) and Communications Societies, including the G. Marconi Prize Paper Award in Wireless Communications. He also received the IEEE-SPS Nobert Wiener Society Award (2019); Technical Achievement Awards from the SP Society (2000) and from EURASIP (2005); the IEEE ComSoc Education Award (2019); the G. W. Taylor Award for Distinguished Research from the University of Minnesota, and the IEEE Fourier Technical Field Award (inaugural recipient in 2015). He is a Fellow of the National Academy of Inventors, IEEE and EURASIP, and has served the IEEE in a number of posts, including that of a Distinguished Lecturer for the IEEE-SPS.
Deep Learning and 3D Geometry
While Deep Learning in computer vision had been focusing on 2D analysis of images, such as 2D object detection or image segmentation, these recent years have seen the development of many approaches applying the power of Deep Learning to 3D perception from color images, to to solve problems that were very challenging or even impossible a few years ago. Because Deep Learning and 3D geometry come from very different mathematical worlds, one has to find smart ways to connect them, and benefit from These approaches often rely on combinations of Deep Learning applied to 2D images and 3D geometry techniques. In this course, we will review and explain recent approaches to Deep Learning and 3D geometry problems, including 3D object pose estimation, 3D hand pose estimation, feature point detection, self-learning for depth prediction, and 3D scene understanding.
Basic knowledge of Deep Learning applied to computer vision and 3D Geometry
Vincent Lepetit is a director of research at ENPC ParisTech since 2019. Prior to being at ENPC, he was a full professor at the Institute for Computer Graphics and Vision, Graz University of Technology, Austria, and before that, a senior researcher at the Computer Vision Laboratory (CVLab) of EPFL, Switzerland. His research interest are at the interface between Machine Learning and 3D Computer Vision, and currently focus on 3D scene understanding from images. He often serves as an area chair for the major computer vision conferences (CVPR, ICCV, ECCV) and is an associate editor for PAMI, IJCV, and CVIU.
The field of graph signal processing extends classical signal processing tools to signals (data) with an irregular structure that can be characterized my means of a graph (e.g., network data). One of the cornerstones of this field are graph filters, direct analogues of time-domain filters, but intended for signals defined on graphs. In this course, we introduce the field of graph signal processing and specifically give an overview of the graph filtering problem. We look at the family of finite impulse response (FIR) and infinite impulse response (IIR) graph filters and show how they can be implemented in a distributed manner. To further limit the communication and computational complexity of such a distributed implementation, we also generalize the state-of-the-art distributed graph filters to filters whose weights show a dependency on the nodes sharing information. These so-called edge-variant graph filters yield significant benefits in terms of filter order reduction and can be used for solving specific distributed optimization problems with an extremely fast convergence. Finally, we will overview how graph filters can be used in deep learning applications involving data sets with an irregular structure. Different types of graph filters can be used in the convolution step of graph convolutional networks leading to different trade-offs in performance and complexity. The numerical results presented in this talk illustrate the potential of graph filters in distributed optimization and deep learning.
Basics in digital signal processing, linear algebra, optimization and machine learning.
Geert Leus received the M.Sc. and Ph.D. degree in Electrical Engineering from the KU Leuven, Belgium, in June 1996 and May 2000, respectively. Geert Leus is now an "Antoni van Leeuwenhoek" Full Professor at the Faculty of Electrical Engineering, Mathematics and Computer Science of the Delft University of Technology, The Netherlands. His research interests are in the broad area of signal processing, with a specific focus on wireless communications, array processing, sensor networks, and graph signal processing. Geert Leus received a 2002 IEEE Signal Processing Society Young Author Best Paper Award and a 2005 IEEE Signal Processing Society Best Paper Award. He is a Fellow of the IEEE and a Fellow of EURASIP. Geert Leus was a Member-at-Large of the Board of Governors of the IEEE Signal Processing Society, the Chair of the IEEE Signal Processing for Communications and Networking Technical Committee, a Member of the IEEE Sensor Array and Multichannel Technical Committee, and the Editor in Chief of the EURASIP Journal on Advances in Signal Processing. He was also on the Editorial Boards of the IEEE Transactions on Signal Processing, the IEEE Transactions on Wireless Communications, the IEEE Signal Processing Letters, and the EURASIP Journal on Advances in Signal Processing. Currently, he is the Chair of the EURASIP Technical Area Committee on Signal Processing for Multisensor Systems, a Member of the IEEE Signal Processing Theory and Methods Technical Committee, a Member of the IEEE Big Data Special Interest Group, an Associate Editor of Foundations and Trends in Signal Processing, and the Editor in Chief of EURASIP Signal Processing.
These 3 lectures will cover several neural models for high performance NLP algorithms covering applications such as machine translation, reading comprehension, natural language generation, and semantic parsing.
Mathematics at the level of an undergraduate degree in engineering, computer science, math and physics: basic multivariate calculus, probability theory, and linear algebra.
Salim is an IBM Fellow and CTO for Translation Technologies at IBM T. J. Watson Research Center. Dr. Roukos joined Bolt Beranek and Newman from 1980 through 1989, where he was a Senior Scientist in charge of projects in speech compression, time scale modification, speaker identification, word spotting, and spoken language understanding. He was an Adjunct Professor at Boston University in 1988 before joining IBM in 1989. Dr. Roukos has served as Chair of the IEEE Digital Signal Processing Committee in 1988. Salim Roukos has lead teams at IBM T.J. Watson research Center that focused on various problems using machine learning techniques for natural language processing. The group pioneered many of the statistical methods for NLP from statistical parsing, to natural language understanding, to statistical machine translation and machine translation evaluation metrics (BLEU metric). Roukos has over a 150 publications in the speech and language areas and over two dozen patents. Roukos was the lead of the group which introduced the first commercial statistical language understanding system for conversational telephony systems (IBM ViaVoice Telephony) in 2000 and the first statistical machine translation product for Arabic-English translation in 2003. More recently, his team created the IBM Watson Language Translator and the custom models for IBM Natural Language Understanding. Roukos is also a fellow of the Association for Computational Linguistics.
The past few years have seen a dramatic increase in the performance of recognition systems thanks to the introduction of deep networks for representation learning. However, the mathematical reasons for this success remain elusive. For example, a key issue is that the neural network training problem is nonconvex, hence optimization algorithms are not guaranteed to return a global minima. The first part of this tutorial will overview recent work on the theory of deep learning that aims to understand how to design the network architecture, how to regularize the network weights, and how to guarantee global optimality. The second part of this tutorial will present sufficient conditions to guarantee that local minima are globally optimal and that a local descent strategy can reach a global minima from any initialization. Such conditions apply to problems in matrix factorization, tensor factorization and deep learning. The third part of this tutorial will present an analysis of dropout for matrix factorization, and establish connections
Basic understanding of sparse and low-rank representation and non-convex optimization.
Rene Vidal is a Professor of Biomedical Engineering and the Innaugural Director of the Mathematical Institute for Data Science at The Johns Hopkins University. His research focuses on the development of theory and algorithms for the analysis of complex high-dimensional datasets such as images, videos, time-series and biomedical data. Dr. Vidal has been Associate Editor of TPAMI and CVIU, Program Chair of ICCV and CVPR, co-author of the book 'Generalized Principal Component Analysis' (2016), and co-author of more than 200 articles in machine learning, computer vision, biomedical image analysis, hybrid systems, robotics and signal processing. He is a fellow of the IEEE, IAPR and Sloan Foundation, a ONR Young Investigator, and has received numerous awards for his work, including the 2012 J.K. Aggarwal Prize for "outstanding contributions to generalized principal component analysis (GPCA) and subspace clustering in computer vision and pattern recognition” as well as best paper awards in machine learning, computer vision, controls, and medical robotics.
Big data holds the potential to solve many challenging problems, and one of them is understanding natural languages, which still faces tremendous challenges. It has been shown that in areas such as question answering and conversation, domain knowledge is indispensable. Thus, how to acquire, represent, and apply domain knowledge for text understanding is of critical importance. In this short course, I will use understanding short text (search queries, tweets, captions, titles, etc) as an example to demonstrate the challenges in this domain. Short text understanding is crucial to many applications. In addition to known difficulties in natural language understanding, short texts do not always observe the syntax of a written language. As a result, traditional natural language processing methods cannot be easily applied. Second, short texts usually do not contain sufficient statistical signals to support many state-of-the-art approaches for text processing such as topic modeling. Third, short texts are usually more ambiguous. I will go over various techniques in knowledge acquisition, representation, and inferencing has been proposed for text understanding, and will describe massive structured and semi-structured data that have been made available in the recent decade that directly or indirectly encode human knowledge, turning the knowledge representation problems into a computational grand challenge with feasible solutions insight.
Haixun Wang is an IEEE fellow, a chief-editor of the IEEE Data Engineering Bulletin, and a VP of Engineering and Distinguished Scientist at WeWork, where he leads the engineering team as well as the Research and Applied Science division. He was Director of Natural Language Processing at Amazon. Before Amazon, he led the NLP Infra team in Facebook working on Query and Document Understanding. From 2013 to 2015, he was with Google Research, working on natural language processing. From 2009 to 2013, he led research in semantic search, graph data processing systems, and distributed query processing at Microsoft Research Asia. His knowledge base project Probase has created significant impact in industry and academia. He had been a research staff member at IBM T. J. Watson Research Center from 2000 – 2009. He was Technical Assistant to Stuart Feldman (Vice President of Computer Science of IBM Research) from 2006 to 2007, and Technical Assistant to Mark Wegman (Head of Computer Science of IBM Research) from 2007 to 2009. He received the Ph.D. degree in Computer Science from the University of California, Los Angeles in 2000. He has published more than 150 research papers in referred international journals and conference proceedings. He served as PC Chairs of conferences such as CIKM’12, and he is on the editorial board of journals such as IEEE Transactions of Knowledge and Data Engineering (TKDE) and Journal of Computer Science and Technology (JCST). He won the best paper award in ICDE 2015, 10-year best paper award in ICDM 2013, and best paper award of ER 2009.