GlobalSIP 2017:

Symposium on Sparse Signal Processing and Deep Learning

[Download the PDF Call for Papers]

The Sparse Signal Processing and Deep Learning symposium will explore deep connection between sparsity of signals and deep learning theory, and will thus focus on novel signal processing ideas and results, both experimental and theoretical, in learning compact and meaningful signal representations, in efficient signal sampling and sensing, and in computational methods for highdimensional big data sets that pervade the current information age, and spare implementation of deep networks using novel hardware technologies.

Distinguished Symposium Talk

Muriel Medard

EECS, Massachusetts Institute of Technology

Some connections between sparse signal processing and information theory

Abstract
Sparse signal processing has roots in information theory but is concerned with different metrics than the ones generally associated with information theory. In particular, it considers complexity of reconstruction, which tends to be neglected in information theory, but it does not assess fundamental limits of reliably achievable rates, which are commonly the key quantities of interest in information theory. In this talk, we present a perspective and results linking the two types of metrics, where we envision sparse signal processing in terms of a suboptimal form of coding, where reducing the complexity of reconstruction leads to a rate penalty. Using this framework, we envisage channel coding, source coding, distributed source coding and network coding, and show how we may use sparse signal reconstruction to provide information theoretically suboptimal but still highly efficient techniques.

Biography
Muriel Médard is the Cecil H. Green Professor in the Electrical Engineering and Computer Science (EECS) Department at MIT and leads the Network Coding and Reliable Communications Group at the Research Laboratory for Electronics at MIT.

She has co-founded three companies to commercialize network coding, CodeOn, Steinwurf and Chocolate Cloud. She has served as editor for many publications of the Institute of Electrical and Electronics Engineers (IEEE), of which she was elected Fellow, and she is currently Editor in Chief of the IEEE Journal on Selected Areas in Communications She was President of the IEEE Information Theory Society in 2012, and served on its board of governors for eleven years. She has served as technical program committee co-chair of many of the major conferences in information theory, communications and networking.

She received the 2009 IEEE Communication Society and Information Theory Society Joint Paper Award, the 2009 William R. Bennett Prize in the Field of Communications Networking, the 2002 IEEE Leon K. Kirchmayer Prize Paper Award and several conference paper awards. She was co-winner of the MIT 2004 Harold E. Edgerton Faculty Achievement Award, received the 2013 EECS Graduate Student Association Mentor Award and served as Housemaster for seven years. In 2007 she was named a Gilbreth Lecturer by the U.S. National Academy of Engineering. She received the 2016 IEEE Vehicular Technology James Evans Avant Garde Award, the 2017 Aaron Wyner Distinguished Service Award from the IEEE Information Theory Society and the 2017 IEEE Communications Society Edwin Howard Armstrong Achievement Award.

Schedule

Submissions are welcome on topics including:

• Connections between sparse auto encoders and sparse representation
• Floating point operation optimization of deep networks
• Sparse coding, sparse representations, and dictionary learning
• Sparse and low-rank approximation algorithms
• Spare sequence-to-sequence learning
• Learning on graphs
• Connections between learning rate and sampling rate
• Sparsity and super resolution
• Recurrent neural networks for periodic and quasi-periodic signals
• Phase retrieval and bilinear problems
• End-to-end deep-learning vision or speech recognition system
• Advanced supervised and unsupervised deep learning algorithms
• Sparse explainable networks
• VLSI implementation of Tensor sketching and factorizations
• Compressed Learning – compressive sensing for learning: new theory and methods
• Dimensionality reduction, feature extraction, classification, detection, and source separation
• Geometric Wavelet Theory
• Sparsity measures in approximation theory, information theory and statistics
• Regularization theory with low-complexity / lowdimensional structures
• Statistical models and algorithms for sparsity
• Sparse network theory and analysis
• Tree-to-Tree learning
• Deep-learning software and hardware architecture
• Big data applications

Paper Submission

Prospective authors are invited to submit full-length papers (up to 4 pages for technical content, an optional 5th page containing only references) and extended abstracts (up to 2 pages, for paperless industry presentations and Ongoing Work presentations). Manuscripts should be original (not submitted/published anywhere else) and written in accordance with the standard IEEE double-column paper template. Accepted full-length papers will be indexed on IEEE Xplore. Accepted abstracts will not be indexed in IEEE Xplore, however the abstracts and/or the presentations will be included in the IEEE SPS SigPort. Accepted papers and abstracts will be scheduled in lecture and poster sessions. Submission is through the GlobalSIP website at http://2017.ieeeglobalsip.org/Papers.asp.

Notice: The IEEE Signal Processing Society enforces a “no-show” policy. Any accepted paper included in the final program is expected to have at least one author or qualified proxy attend and present the paper at the conference. Authors of the accepted papers included in the final program who do not attend the conference will be subscribed to a “No-Show List”, compiled by the Society. The “no-show” papers will not be published by IEEE on IEEEXplore or other public access forums, but these papers will be distributed as part of the on-site electronic proceedings and the copyright of these papers will belong to the IEEE.

Organizing Committee

General Chair

Peter Chin, Boston University and Systems & Technology Research, Boston, USA

Technical Co-Chairs

Piya Pal, University of Maryland, College Park, USA
Seung-Jun Kim, Univ. of Maryland, Baltimore Co., USA
Trac D. Tran, Johns Hopkins University, Baltimore, USA