Asilomar Schedule 04/11/2019

# Asilomar Schedule 04/11/2019 ###### Tags: `Others` #### 07:30 - 09:00 Breakfast Crocker (Dining Hall) #### 08:00 - 18:00 Registration #### 08:15 - 09:45 MA1a: Conference Welcome and Plenary Session Chapel ###### Session MA1a: Fundamental limits of deep neural network learning - Prof. Helmut Bölcskei, ETH Zurich <details> <summary> Details </summary> Abstract We develop the fundamental limits of learning in deep neural networks by characterizing what is possible if no constraints on the learning algorithm and the amount of training data are imposed. Concretely, we consider Kolmogorov-optimal approximation through deep neural networks with the guiding theme being a relation between the complexity of the function (class) to be approximated and the complexity of the approximating network in terms of connectivity and memory requirements for storing the network topology and the associated quantized weights. The theory we develop educes remarkable universality properties of deep networks. Specifically, deep networks are optimal approximants for vastly different function classes such as affine systems and Gabor systems. In addition, deep networks provide exponential approximation accuracy—i.e., the approximation error decays exponentially in the number of non-zero weights in the network—of widely different functions including the multiplication operation, polynomials, sinusoidal functions, general smooth functions, and even one-dimensional oscillatory textures and fractal functions such as the Weierstrass function, both of which do not have any known methods achieving exponential approximation accuracy. We also show that in the approximation of sufficiently smooth functions finite-width deep networks require strictly smaller connectivity than finite-depth wide networks. Biography Helmut Bölcskei was born in Mödling, Austria on May 29, 1970, and received the Dipl.-Ing. and Dr. techn. degrees in electrical engineering from Vienna University of Technology, Vienna, Austria, in 1994 and 1997, respectively. In 1998 he was with Vienna University of Technology. From 1999 to 2001 he was a postdoctoral researcher in the Information Systems Laboratory, Department of Electrical Engineering, and in the Department of Statistics, Stanford University, Stanford, CA. He was in the founding team of Iospan Wireless Inc., a Silicon Valley-based startup company (acquired by Intel Corporation in 2002) specialized in multiple-input multiple-output (MIMO) wireless systems for high-speed Internet access, and was a co-founder of Celestrius AG, Zurich, Switzerland. From 2001 to 2002 he was an Assistant Professor of Electrical Engineering at the University of Illinois at Urbana-Champaign. He has been with ETH Zurich since 2002, where he is a Professor of Mathematical Information Science in the Department of Electrical Engineering, also associated with the Department of Mathematics. He was a visiting researcher at Philips Research Laboratories Eindhoven, The Netherlands, ENST Paris, France, and the Heinrich Hertz Institute Berlin, Germany. His research interests are in applied mathematics, machine learning theory, mathematical signal processing, data science, and statistics. He received the 2001 IEEE Signal Processing Society Young Author Best Paper Award, the 2006 IEEE Communications Society Leonard G. Abraham Best Paper Award, the 2010 Vodafone Innovations Award, the ETH "Golden Owl" Teaching Award, is a Fellow of the IEEE, a 2011 EURASIP Fellow, was a Distinguished Lecturer (2013-2014) of the IEEE Information Theory Society, an Erwin Schrödinger Fellow (1999-2001) of the Austrian National Science Foundation (FWF), was included in the 2014 Thomson Reuters List of Highly Cited Researchers in Computer Science, and is the 2016 Padovani Lecturer of the IEEE Information Theory Society. He served as an associate editor of the IEEE Transactions on Information Theory, the IEEE Transactions on Signal Processing, the IEEE Transactions on Wireless Communications, and the EURASIP Journal on Applied Signal Processing. He was editor-in-chief of the IEEE Transactions on Information Theory during the period 2010-2013 and served on the editorial board of the IEEE Signal Processing Magazine, “Foundations and Trends in Communication and Information Theory”, and “Foundations and Trends in Networking”. He was TPC co-chair of the 2008 IEEE International Symposium on Information Theory and the 2016 IEEE Information Theory Workshop and served on the Board of Governors of the IEEE Information Theory Society. He has been a delegate for faculty appointments of the president of ETH Zurich since 2008. </details> #### 09:45 - 10:15 Coffee Social #### 10:15 - 11:55 * MA1b: Beyond Massive MIMO (Invited)(Nautilus) <details> <summary> Details </summary> MA1b-1: SUPER-DIRECTIVE ANTENNA ARRAYS: FUNDAMENTALS AND NEW PERSPECTIVES Thomas Marzetta; New York University MA1b-2: USING MASSIVE MIMO ARRAYS FOR JOINT COMMUNICATION AND SENSING Stefano Buzzi; University of Cassino and Lazio Meridionale Carmen D'Andrea; University of Cassino and Lazio Meridionale Marco Lops; University ”Federico II” of Naples MA1b-3: CAN A LARGE INTELLIGENT SURFACE BE USED FOR POSITIONING IF IT ONLY CAN MEASURE ENERGY? Juan Vidal Alegria; Lund University Fredrik Rusek; Lund University MA1b-4: RADIOWEAVES FOR EFFICIENT CONNECTIVITY: ANALYSIS AND IMPACT OF CONSTRAINTS IN ACTUAL DEPLOYMENTS Liesbet Van der Perre; KU Leuven Erik G. Larsson; Linköping University Fredrik Tufvesson; Lund University Lieven De Strycker; KU Leuven Emil Björnson; Linköping University Ove Edfors; Lund University </details> * MA2b: Advances in Sequential Estimation, Sampling, and Testing (Invited) (Surf & Sand) <details> <summary> Details </summary> MA2b-1: NONPARAMETRIC GENERALIZATIONS OF THE SEQUENTIAL PROBABILITY RATIO TEST Steven Howard; University of California, Berkeley Aaditya Ramdas; Carnegie Mellon University Jon McAuliffe; University of California, Berkeley Jasjeet Sekhon; University of California, Berkeley MA2b-2: INFORMATION-THEORETIC LOWER BOUNDS FOR ADAPTIVE SAMPLING: IS AN ORACLE TOO POWERFUL? Max Simchowitz; University of California, Berkeley Kevin Jamieson; University of Washington MA2b-3: BEST-ARM IDENTIFICATION AND HYPOTHESIS TESTING IN VERY LARGE ACTION SPACES Kevin Jamieson; University of Washington MA2b-4: ARE SAMPLE MEANS IN MULTI-ARMED BANDITS POSITIVELY OR NEGATIVELY BIASED? Jaehyeok Shin; Carnegie Mellon University Aaditya Ramdas; Carnegie Mellon University Alessandro Rinaldo; Carnegie Mellon University </details> * MA3b: New Perspectives on Multiple Access (Invited) (Triton) <details> <summary> Details </summary> MA3b-1: GRANT-FREE MASSIVE RANDOM ACCESS WITH A MASSIVE MIMO RECEIVER Alexander Fengler; Technical University of Berlin Giuseppe Caire; Technical University of Berlin Saeid Haghighatshoar; Technical University of Berlin Peter Jung; Technical University of Berlin MA3b-2: CODED SLOTTED ALOHA OVER THE ON-OFF FADING CHANNEL: PERFORMANCE BOUNDS Gianluigi Liva; German Aerospace Center (DLR) Enrico Paolini; University of Bologna Cedomir Stefanovic; Aalborg University Alexandre Graell i Amat; Chalmers University of Technology MA3b-3: INFORMATION THEORY OF MULTIPLE-ACCESS CHANNELS WITH MANY USERS Yury Polyanskiy; Massachusetts Institute of Technology MA3b-4: PHASE TRANSITION ANALYSIS FOR COVARIANCE BASED MASSIVE RANDOM ACCESS WITH MASSIVE MIMO Zhilin Chen; University of Toronto Wei Yu; University of Toronto </details> * MA4b: Deep Learning for Inverse Problems (Invited) Heather <details> <summary> Details </summary> MA4b-1: DEEP GENERATIVE MODELS AND INVERSE PROBLEMS Alex Dimakis; University of Texas at Austin Ajil Jalal; University of Texas at Austin MA4b-2: ADDRESSING NON-EUCLIDEAN INVERSE PROBLEMS WITH GEOMETRIC DEEP LEARNING Joan Bruna; New York University MA4b-3: GENERALIZATION RISK ANALYSIS FOR NEURAL PROXIMAL GRADIENT DESCENT ALGORITHMS Morteza Mardani; Stanford University MA4b-4: DEEP DECODER: CONCISE IMAGE REPRESENTATIONS FROM UNTRAINED NON-CONVOLUTIONAL NETWORKS Reinhard Heckel; Rice University Paul Hand; Northeastern University </details> * MA5b: Graph Signal Processing: Advances in Sampling, Filtering, Reconstruction (Invited) Scripps <details> <summary> Details </summary> MA5b-1: DISTRIBUTED ADAPTIVE LEARNING OF GRAPH PROCESSES VIA IN-NETWORK PROJECTIONS Paolo Di Lorenzo; Sapienza University of Rome Sergio Barbarossa; Sapienza University of Rome Stefania Sardellitti; Sapienza University of Rome MA5b-2: ON DISTRIBUTED CONSENSUS BY A CASCADE OF GENERALIZED GRAPH FILTERS Mario Coutino; Delft University of Technology Geert Leus; Delft University of Technology MA5b-3: AN EFFICIENT ALGORITHM FOR GRAPH LAPLACIAN OPTIMIZATION BASED ON EFFECTIVE RESISTANCES Eduardo Pavez; University of Southern California Antonio Ortega; University of Southern California MA5b-4: NETWORK RECONSTRUCTION FROM GRAPH-STATIONARY SIGNALS WITH HIDDEN VARIABLES Andrei Buciulea; King Juan Carlos University Cristobal Cabrera; King Juan Carlos University Antonio Marques; King Juan Carlos University </details> * MA6b: Compilation for Spatial Computing Architectures (Invited) Toyon <details> <summary> Details </summary> MA6b-1: HETEROCL: A MULTI-PARADIGM PROGRAMMING INFRASTRUCTURE FOR RECONFIGURABLE COMPUTING Yi-Hsiang Lai; Cornell University Zhiru Zhang; Cornell University MA6b-2: PROGRAMMATIC CONTROL OF A COMPILER FOR GENERATING HIGH-PERFORMANCE SPATIAL HARDWARE Hongbo Rong; Intel Labs MA6b-3: ANALYSIS METHODS FOR MEMORY IN HIGH-LEVEL SYNTHESIS George Constantinides; Imperial College London MA6b-4: A HARDWARE-SOFTWARE BLUEPRINT FOR FLEXIBLE DEEP LEARNING SPECIALIZATION Thierry Moreau; University of Washington </details> * MA7b: Modeling, Optimization, and Machine Learning for Computational Imaging (Invited) Acacia <details> <summary> Details </summary> MA7b-1: DEEP NETWORKS AND THE MULTIPLE MANIFOLD PROBLEM Dar Gilboa; Columbia University Sam Buchanan; Columbia University John Wright; Columbia University MA7b-2: MODEL-BASED ITERATIVE RECONSTRUCTION FOR ECHO PLANAR IMAGING: METHODS AND APPLICATIONS Uten Yarach; Mayo Clinic Matt Bernstein; Mayo Clinic John Huston III; Mayo Clinic Myung-Ho In; Mayo Clinic Daehun Kang; Mayo Clinic Yunhong Shu; Mayo Clinic Erin Gray; Mayo Clinic Nolan Meyer; Mayo Clinic Joshua Trzasko; Mayo Clinic MA7b-3: RELIABLE DEEP LEARNING FOR COMPUTATIONAL MICROSCOPY Lei Tian; Boston University Yujia Xue; Boston University Shiyi Cheng; Boston University Yunzhe Li; Boston University MA7b-4: LOW-RANK MODELING OF LOCAL SINOGRAM NEIGHBORHOODS WITH APPLICATION TO X-RAY CT AND PET Rodrigo A. Lobos; University of Southern California Richard M. Leahy; University of Southern California Justin P. Haldar; University of Southern California </details> * MA8b1: Audio, Video, and Speech Processing Merrill <details> <summary> Details </summary> MA8b1-1: VARIETY-BASED BACKGROUND SUBTRACTION FOR NONLINEAR TRAJECTORY TRACKING Amr Elnakeeb; University of Southern California Urbashi Mitra; University of Southern California MA8b1-2: AUTOMATED AUGMENTATION WITH REINFORCEMENT LEARNING AND GANS FOR ROUST IDENTIFICATION OF TRAFFIC SIGNS USING FRONT CAMERA IMAGES Sohini Roychowdhury; Volvocars USA Lars Tornberg; Volvocars Robin Halfvordsson; Chalmers University of Technology Jonatan Nordh; Chalmers University of Technology Adam Suhren Gustafsson; Chalmers University of Technology Joel Wall; Chalmers University of Technology Mattias Westerberg; Chalmers University of Technology Adam Wirehed; Chalmers University of Technology Zhanying Hu; University of California, Berkeley Meng Pan; University of California, Berkeley Louis Tilloy; University of California, Berkeley MA8b1-3: VIDEO-BASED WETTING DETECTION FOR BLENDED FABRICS Xianpeng Liu; North Carolina State University Chau-Wai Wong; North Carolina State University MA8b1-4: ADAPTIVE VIDEO SUBSAMPLING FOR ENERGY-EFFICIENT OBJECT DETECTION Divya Mohan; University of California, Berkeley Sameeksha Katoch; Arizona State University Suren Jayasuriya; Arizona State University Pavan Turaga; Arizona State University Andreas Spanias; Arizona State University MA8b1-5: MUTUAL INFORMATION AND CELP VOICE CODEC PERFORMANCE ANALYSIS AND PREDICTION Jerry Gibson; University of California, Santa Barbara MA8b1-6: ADAPTIVE FEEDBACK CANCELLATION FOR HEARING AIDS USING THE PREDICTION-ERROR METHOD WITH ORTHONORMAL BASIS FUNCTIONS Sahar Hashemgeloogerdi; University of Rochester Mark Bocko; University of Rochester MA8b1-7: VOICE TRANSFORMATION USING TWO-LEVEL DYNAMIC WARPING Al-Waled Al-Dulaimi; Utah State University Todd Moon; Utah State University Jacob Gunther; Utah State University MA8b1-8: DILATED CONVOLUTIONAL RECURRENT NEURAL NETWORK FOR MONAURAL SPEECH ENHANCEMENT Shadi Pirhosseinloo; University of Kansas Jonathan Scott Brumberg; University of Kansas </details> * MA8b2: DOA Estimation, Beamforming, and Localization Merrill <details> <summary> Details </summary> MA8b2-1: CHIRP SOURCE DOA ESTIMATION USING FREQUENCY-SHIFT AND COMPRESSIVE DCFT Luay Ali Al Irkhis; Wright State University Arnab Shaw; Wright State University MA8b2-2: NEAR-FIELD LOCALIZATION USING ANTENNA ARRAYS Benjamin Friedlander; University of California, Santa Cruz MA8b2-3: GENERAL FIRST-ORDER RESULTS FOR PASSIVE LOCALIZATION FROM TWO SENSOR ARRAYS Louis Scharf; Colorado State University L. Todd McWhorter; Brooks Canyon, LLC James Given; Naval Research LaB Margaret Cheney; Colorado State University MA8b2-4: 1-BIT SPARSE GRIDLESS SUPER-RESOLUTION DOA ESTIMATION FOR COPRIME ARRAYS Anupama Govinda Raj; Georgia Institute of Technology James McClellan; Georgia Institute of Technology MA8b2-5: BLIND CO-CHANNEL SOURCE SEPARATION FOR PULSE-ON-PULSE INTERFERENCE Douglas Schuyler; Lockheed Martin Corporation Ben Johnson; Lockheed Martin Corporation Mitchel McGough; Lockheed Martin Corporation MA8b2-6: COMPRESSIVE BEAMFORMING AND DIRECTIONAL SOUND RECONSTRUCTION USING THE KRONECKER ARRAY TRANSFORM Marcelo Abdala Daher; University of São Paulo Carlos A. Prete Jr.; University of São Paulo Vítor Heloz Nascimento; University of São Paulo Bruno S. Masiero; University of Campinas MA8b2-7: ON ESPRITWITH MULTIPLE COPRIME-INVARIANCES Po-Chih Chen; California Institute of Technology P. P. Vaidyanathan; California Institute of Technology MA8b2-8: DOPPLER-AIDED POSITION ESTIMATION FOR HS-GNSS Francois Vincent; University of Toulouse Eric Chaumette; University of Toulouse Jordi Vila-Valls; University of Toulouse </details> * MA8b3: Array Processing for Signal Detection and Classification Merrill <details> <summary> Details </summary> MA8b3-1: ADAPTIVE SIGNAL DETECTION IN SUBSPACE INTERFERENCE WITH UNCERTAIN PRIOR KNOWLEDGE Yuan Jiang; Stevens Institute of Technology Hongbin Li; Stevens Institute of Technology Muralidhar Rangaswamy; Air Force Research Laboratory / RYAR MA8b3-2: LOW-COMPLEXITY NEURAL NETWORK-BASED MIMO DETECTOR USING PERMUTED DIAGONAL MATRIX Siyu Liao; Rutgers University Chunhua Deng; Rutgers University Lingjia Liu; Virginia Tech Bo Yuan; Rutgers University MA8b3-3: QUICKEST DETECTION OF A DYNAMIC ANOMALY IN A SENSOR NETWORK Georgios Rovatsos; University of Illinois at Urbana-Champaign George Moustakides; University of Patras Venugopal Veeravalli; University of Illinois at Urbana-Champaign MA8b3-4: MULTI-CHANNEL TARGET DETECTION FOR MARITIME RADAR Elias Abouta; University of New South Wales Luke Rosenberg; DST Group MA8b3-5: CLUTTER CANCELLATION IN PASSIVE RADAR AS A DUAL BASIS PROJECTION Stephen Searle; University of South Australia Stephen Howard; Defence Science and Technology Group MA8b3-6: PROBABILITY OF DETECTION FOR UNAMBIGUOUS DOPPLER FREQUENCIES IN PULSE RADARS USING THE CHINESE REMAINDER THEOREM AND SUBPULSE PROCESSING Fernando Darío Almeida García; State University of Campinas André Saito Guerreiro; State University of Campinas Gustavo Rodrigues de Lima Tejerina; State University of Campinas José Cândido Silveira Santos Filho; State University of Campinas Gustavo Fraidenraich; State University of Campinas Michel Daoud Yacoub; State University of Campinas Marco Antonio Miguel Miranda; Bradar - Embraer Defense and Security Higor Cioqueta; Bradar - Embraer Defense and Security MA8b3-7: FRACTIONAL SPECTROGRAM FOR CHARACTERIZING AND CLASSIFYING VIBRATING OBJECTS IN SAR IMAGES Francisco Perez; University of New Mexico Balu Santhanam; University of New Mexico Bipesh Shrestha; University of New Mexico Walter Gerstle; University of New Mexico Majeed M. Hayat; Marquette University </details> #### 12:00 - 13:00 Lunch Crocker (Dining Hall) #### 13:30 - 15:10 * MP1a: MIMO for mmWave and THz (Invited) Nautilus <details> <summary> Details </summary> MP1a-1: A MASSIVE 28 GHZ SWITCHED ARRAY SOUNDER FOR DYNAMIC CHANNEL CHARACTERIZATION Harsh Tataria; Lund University Erik Bengtsson; Sony Research Peter C. Karlsson; Sony Research Fredrik Tufvesson; Lund University MP1a-2: MANAGING HARDWARE IMPAIRMENTS IN HYBRID MILLIMETER WAVE MIMO SYSTEMS: A DICTIONARY LEARNING-BASED APPROACH Joan Palacios; Imdea Networks Nuria Gonzalez Prelcic; University of Texas at Austin Joerg Widmer; Imdea Networks MP1a-3: A MACHINE LEARNING SOLUTION FOR BEAM TRACKING IN MMWAVE SYSTEMS Daoud Burghal; University of Southern California Naveed A. Abbasi; University of Southern California Andreas F. Molisch; Collaborator MP1a-4: FINITE-ALPHABET WIENER FILTER PRECODING FOR MMWAVE MASSIVE MU-MIMO SYSTEMS Oscar Castañeda; Cornell University Sven Jacobsson; Chalmers University of Technology Giuseppe Durisi; Chalmers University of Technology Tom Goldstein; University of Maryland Christoph Studer; Cornell University </details> * MP2a: Distributed Learning in Multi-Agent Environments (Invited) Surf & Sand <details> <summary> Details </summary> MP2a-1: DESIGN STRATEGIES FOR SPARSE CONTROL OF RANDOM TIME-VARYING NETWORKS Mario Coutino; Delft University of Technology Elvin Isufi; University of Pennsylvania Fernando Gama; University of Pennsylvania Alejandro Ribeiro; University of Pennsylvania Geert Leus; Delft University of Technology MP2a-2: ONLINE NON-CONVEX OPTIMIZATION AND LEARNING BASED ON SUCCESSIVE CONVEX APPROXIMATION Paolo Di Lorenzo; Sapienza University of Rome Mattia Merluzzi; Sapienza University of Rome MP2a-3: DISTRIBUTED EMPIRICAL RISK MINIMIZATION OVER DIRECTED GRAPHS Ran Xin; Tufts University Anit Kumar Sahu; The Bosch Center for Artificial Intelligence Soummya Kar; Carnegie Mellon University Usman Khan; Tufts University MP2a-4: DISTRIBUTED LEARNING OVER NETWORKS UNDER SUBSPACE CONSTRAINTS Roula Nassif; Ecole polytechnique fédérale de Lausanne (EPFL) Stefan Vlaski; Ecole polytechnique fédérale de Lausanne (EPFL) Ali Sayed; Ecole polytechnique fédérale de Lausanne (EPFL) </details> * MP3a: Optimization Methods for Wireless Communications (Invited) Triton <details> <summary> Details </summary> MP3a-1: UPLINK-DOWNLINK CHANNEL COVARIANCE TRANSFORMATIONS AND PRECODING DESIGN FOR FDD MASSIVE MIMO Mahdi Barzegar Khalilsarai; Technical University of Berlin Saeid Haghighatshoar; Technical University of Berlin Giuseppe Caire; Technical University of Berlin MP3a-2: ZERO CROSSING MODULATION FOR COMMUNICATION WITH TEMPORALLY OVERSAMPLED 1-BIT QUANTIZATION Gerhard Fettweis; Technische Universität Dresden Meik Dörpinghaus; Technische Universität Dresden Sandra Bender; Technische Universität Dresden Martin Schlüter; Technische Universität Dresden MP3a-3: OPTIMIZATION FOR DATA-DRIVEN WIRELESS SENSOR SCHEDULING Marcos Vasconcelos; University of Southern California Urbashi Mitra; University of Southern California MP3a-4: DISTRIBUTED STOCHASTIC OPTIMIZATION IN NETWORKS WITH VARIANCE REDUCTION Yuejie Chi; Carnegie Mellon University </details> * MP4a: Geometric Deep Learning 1 (Invited) Heather <details> <summary> Details </summary> MP4a-1: SCALABLE END-TO-END CLUSTERING WITH GRAPH NEURAL NETWORKS Nicholas Choma; New York University Joan Bruna; New York University MP4a-2: POSITION-AWARE GRAPH NEURAL NETWORKS Jure Leskovec; Stanford University MP4a-3: HODGENET: FLOW INTERPOLATION IN GRAPHS T. Mitchell Roddenberry; Rice University Santiago Segarra; Rice University MP4a-4: GRAPH NEURAL NETWORK ARCHITECTURES FOR GRAPH OUTPUT SIGNALS Samuel Rey-Escudero; King Juan Carlos University Victor Manuel Tenorio; King Juan Carlos University Luca Martino; King Juan Carlos University Antonio Marques; King Juan Carlos University </details> * MP5a: Compressive Sensing and Line Spectral Estimation (Invited) Scripps <details> <summary> Details </summary> MP5a-1: SELF-CALIBRATED SUPER RESOLUTION Maxime Ferreira Da Costa; Carnegie Mellon University Yuejie Chi; Carnegie Mellon University MP5a-2: EMERGENT SPARSITY IN VARIATIONAL AUTOENCODER MODELS Bin Dai; Tsinghua University David Wipf; Microsoft Research MP5a-3: SUPPORT RECOVERY FOR SPARSE RECOVERY AND NON-STATIONARY BLIND DEMODULATION Youye Xie; Colorado School of Mines Michael Wakin; Colorado School of Mines Gongguo Tang; Colorado School of Mines MP5a-4: SPARSE RECOVERY BEYOND COMPRESSED SENSING Carlos Fernandez-Granda; New York University Brett Bernstein; New York University </details> * MP6a: Signal Processing Advances in Neural Modeling (Invited) Toyon <details> <summary> Details </summary> MP6a-1: A STATE SPACE MODEL FOR DYNAMIC FUNCTIONAL CONNECTIVITY Sourish Chakravarty; Massachusetts Institute of Technology Brian Edlow; Massachusetts General Hospital Emery Brown; Massachusetts Institute of Technology MP6a-2: CHARACTERIZING HIPPOCAMPAL REPLAY USING HYBRID POINT PROCESS FILTERS. Eric Denovellis; Boston University Loren Frank; University of California, San Francisco Uri Eden; Boston University MP6a-3: MODULARITY-BASED DETECTION OF HIGH FREQUENCY OSCILLATIONS AND INTERICTAL EPILEPTOGENIC DISCHARGES IN SCALP EEG Stefan Sumsky; University of Connecticut Farrell Brown; University of Connecticut Tanya Dimitrov; University of Connecticut Taylor Somma; Connecticut Children Medical Center Mark Schomer; Connecticut Children Medical Center Sabato Santaniello; University of Connecticut MP6a-4: A WEARABLE BRAIN MACHINE INTERFACE ARCHITECTURE FOR REGULATION OF ENERGY IN HYPERCORTISOLISM Hamid Fekri Azgomi; University of Houston Rose T. Faghih; University of Houston </details> * MP7a: Mathematical Data Science (Invited) Acacia <details> <summary> Details </summary> MP7a-1: MANIFOLD PROXIMAL POINT ALGORITHMS FOR DUAL PRINCIPAL COMPONENT PURSUIT AND ORTHOGONAL DICTIONARY LEARNING Shixiang Chen; Chinese University of Hong Kong Zengde Deng; Chinese University of Hong Kong Shiqian Ma; University of California, Davis Anthony Man-Cho So; Chinese University of Hong Kong MP7a-2: A BUNDLE-TYPE METHOD FOR DUAL ATOMIC PURSUIT Zhenan Fan; University of British Columbia Yifan Sun; University of British Columbia Michael Friedlander; University of British Columbia MP7a-3: SKETCHING FOR MOTZKIN'S ITERATIVE METHOD FOR LINEAR SYSTEMS Elizaveta Rebrova; University of California, Los Angeles Deanna Needell; University of California, Los Angeles MP7a-4: CONVERGENCE OF ITERATIVE HARD THRESHOLDING VARIANTS WITH APPLICATION TO ASYNCHRONOUS PARALLEL METHODS FOR SPARSE RECOVERY Jamie Haddock; University of California, Los Angeles Deanna Needell; University of California, Los Angeles Alireza Zaeemzadeh; University of Central Florida Nazanin Rahnavard; University of Central Florida </details> * MP8a1: Architectures and Implementations Merrill <details> <summary> Details </summary> MP8a1-1: ASYNCHRONOUS STOCHASTIC COMPUTING Patricia Gonzalez-Guerrero; University of Virginia Mircea Stan; University of Virginia MP8a1-2: IMPLEMENTING FIRST-ORDER OPTIMIZATION METHODS: ALGORITHMIC CONSIDERATIONS AND BESPOKE MICROCONTROLLERS Xinwei Zhang; University of Minnesota John Sartori; University of Minnesota Mingyi Hong; University of Minnesota Sairaj Dhople; University of Minnesota MP8a1-3: A DESIGN FRAMEWORK FOR INVERTIBLE LOGIC Naoya Onizawa; Tohoku University Kaito Nishino; Tohoku University Sean Smithson; McGill University Brett Meyer; McGill University Warren Gross; McGill University Hitoshi Yamagata; Canon Medical Systems Corp. Hiroyuki Fujita; Canon Medical Systems Corp. Takahiro Hanyu; Tohoku University MP8a1-4: CONVERTING UNSTABLE CHALLENGES TO STABLE IN MUX-BASED PHYSICAL UNCLONABLE FUNCTIONS BY BIT-FLIPPING Anoop Koyily; University of Minnesota Keshab Parhi; University of Minnesota MP8a1-5: FIRST-THEN-SECOND EXTREMA SELECTION Ali Al Ghouwayel; Lebanese International University (LIU) Hassan Harb; University of South Brittany / Lebanese University Emmanuel Boutillon; University of South Brittany MP8a1-6: NEURAL NETWORK DPD VIA BACKPROPAGATION THROUGH A NEURAL NETWORK MODEL OF THE PA Chance Tarver; Rice University Liwen Jiang; Rice University Joseph Cavallaro; Rice University Aryan Sefidi; Rice University MP8a1-7: FOURIER-BASED ERROR ANALYSIS FOR COMPUTING WITH ASYNCHRONOUS SIGMA-DELTA STREAMS Stephen Wilson; University of Virginia Patricia Gonzalez-Guerrero; University of Virginia Mircea Stan; University of Virginia MP8a1-8: PERFORMANCE EVALUATION OF A SUM ERROR DETECTION SCHEME FOR DECIMAL ARITHMETIC Clara Schaertl Short; University of Texas at Austin Earl E. Swartzlander, Jr.; University of Texas at Austin </details> * MP8a2: Wireless Networks Merrill <details> <summary> Details </summary> MP8a2-1: BIPARTITE MATCHING MECHANISM FOR FRACTIONAL FREQUENCY REUSE-BASED D2D MULTICAST COMMUNICATIONS Devarani Devi Ningombam; Chosun University Jae-Young Pyun; Chosun University Suk-Seung Hwang; Chosun University Seokjoo Shin; Chosun University MP8a2-2: ACTIVE CONTENT POPULARITY LEARNING VIA QUERY-BY-COMMITTEE FOR EDGE CACHING Srikanth Bommaraveni; University of Luxembourg Thang X. Vu; University of Luxembourg Satyanarayana Vuppala; United Technologies Research Centre Symeon Chatzinotas; University of Luxembourg Björn Ottersten; University of Luxembourg MP8a2-3: JOINT POSITIONING-COMMUNICATIONS SYSTEM DESIGN: DISTRIBUTED COHERENCE AND POSITIONING Sharanya Srinivas; Arizona State University Andrew Herschfelt; Arizona State University Daniel Bliss; Arizona State University MP8a2-4: THE CAPACITY REGION OF THE DETERMINISTIC Y-CHANNEL WITH RELAY COMMON AND PRIVATE MESSAGES Mohamed Salah Ibrahim; University of Virginia Yahya Mohasseb; Military Technical College Mohammed Nafie; Cairo University MP8a2-5: ENERGY-EFFICIENT TRAJECTORY DESIGN FOR UAV-ENABLED WIRELESS COMMUNICATIONS WITH LATENCY CONSTRAINTS Hieu Dinh-Tran; University of Luxembourg Thang X. Vu; University of Luxembourg Symeon Chatzinotas; University of Luxembourg Ottersten Björn; University of Luxembourg MP8a2-6: SELF-ORGANIZED SCHEME FOR UNIQUE CELL ID ASSIGNMENT DURING FEMTOCELL DEPLOYMENT Sinan Khwandah; Solent University John Cosmas; Brunel University Zaharias Zaharis; Aristotle University of Thessaloniki Pavlos Lazaridis; University of Huddersfield Albena Mihovska; Aarhus University MP8a2-7: ON MULTI-USER BINARY COMPUTATION OFFLOADING IN THE FINITE-BLOCK-LENGTH REGIME Mahsa Salmani; McMaster University Timothy N. Davidson; McMaster University MP8a2-8: INCREASING RELIABLE COVERAGE FOR MARITIME COMMUNICATIONS Ronald Raulefs; German Aerospace Center (DLR) Wei Wang; Chian'in University MP8a2-9: AVERAGE AGE OF INFORMATION IN MULTI-SOURCE SELF-PREEMPTIVE STATUS UPDATE SYSTEMS WITH PACKET DELIVERY ERRORS Shahab Farazi; Worcester Polytechnic Institute Andrew Klein; Western Washington University Donald Brown; Worcester Polytechnic Institute </details> * MP8a3: Networks: Models and Systems Merrill <details> <summary> Details </summary> MP8a3-1: DECENTRALIZED INFORMATION FILTERING UNDER SKEW-LAPLACE NOISE Jordi Vilà-Valls; ISAE-SUPAERO - University of Toulouse François Vincent; ISAE-SUPAERO - University of Toulouse Pau Closas; Northeastern University MP8a3-2: A MATHEMATICAL FRAMEWORK FOR INTERCONNECTED SYSTEMS OPERATING IN A 1-D NETWORK Jean E. Piou; Massachusetts Institute of Technology MP8a3-3: BIPARTITE STRUCTURED GAUSSIAN GRAPHICAL MODELING VIA ADJACENCY SPECTRAL PRIORS Sandeep Kumar; Hong Kong University of Science and Technology Jiaxi Ying Ying; Hong Kong University of Science and Technology José Vinícius de M. Cardoso; Universidade Federal de Campina Grande Daniel Palomar; Hong Kong University of Science and Technology MP8a3-4: ONLINE LEARNING MODELS FOR CONTENT POPULARITY PREDICTION IN WIRELESS EDGE CACHING Navneet Garg; Heriot-Watt University Bharath Bettagere; Indian Institute of Technology, Dharwad Vimal Bhatia; Indian Institute of Technology, Indore Mathini Sellathurai; Heriot-Watt University Tharmalingam Ratnarajah; Heriot-Watt University MP8a3-5: ON THE LOWER BOUND OF MODULARITY FOR GRAPH FISSION John Roth; Naval Postgraduate School MP8a3-6: FIRE FRONTLINE MONITORING BY ENABLING UAV-BASED VIRTUAL REALITY WITH ADAPTIVE IMAGING RATE Shafkat Islam; Northern Arizona University Abolfazl Razi; Northern Arizona University Fatemeh Afghah; Northern Arizona University Peter Fule; Northern Arizona University MP8a3-7: ENERGY-AWARE MULTI-SERVER MOBILE EDGE COMPUTING: A DEEP REINFORCEMENT LEARNING APPROACH Navid Naderializadeh; Intel Corporation Morteza Hashemi; University of Kansas MP8a3-8: COMPETITIVE INFORMATION SPREAD WITH CONFIRMATION BIAS Yanbing Mao; Binghamton University Emrah Akyol; Binghamton University MP8a3-9: A TRUTHFUL MECHANISM FOR MOBILITY MANAGEMENT IN UNMANNED AERIAL VEHICLES NETWORKS Baocheng Geng; Syracuse University Swastik Brahma; Tennessee State University Pramod Varshney; Syracuse University MP8a3-10: POWER MINIMIZATION IN WIRELESS SENSOR NETWORKS WITH CONSTRAINED AOI: STOCHASTIC OPTIMIZATION Mohammad Moltafet; University of Oulu Markus Leinonen; University of Oulu Marian Codreanu; Linköping University Nikolaos Pappas; Linköping University </details> #### 15:30 - 17:10 * MP1b: Millimeter-Wave MIMO Systems with Low-Complexity Processing (Invited) (Nautilus) <details> <summary> Details </summary> MP1b-1: LEARNING-BASED BEAM ALIGNMENT FOR SINGLE RADIO FREQUENCY-CHAIN LARGE MILLIMETER-WAVE ARRAYS Wai Ming Chan; City University of Hong Kong Hadi Ghauch; Télécom ParisTech Taejoon Kim; University of Kansas Gabor Fodor; Ericsson Research / KTH Royal Institute of Technology MP1b-2: ALL-DIGITAL MASSIVE MIMO UPLINK AND DOWNLINK RATES UNDER A FRONTHAUL CONSTRAINT Yasaman Ettefagh; Chalmers University of Technology Sven Jacobsson; Chalmers University of Technology Giuseppe Durisi; Chalmers University of Technology Christoph Studer; Cornell University MP1b-3: STRUCTURED TENSOR DECOMPOSITION-BASED CHANNEL ESTIMATION FOR WIDEBAND MILLIMETER WAVE MIMO Yuxing Lin; Southeast University Shi Jin; Southeast University Michail Matthaiou; Queen's University Belfast Xiaohu You; Southeast University MP1b-4: SHORT RANGE 3D MIMO MMWAVE CHANNEL RECONSTRUCTION VIA GEOMETRY-AIDED AOAESTIMATION Jarkko Kaleva; University of Oulu Nitin Jonathan Myers; University of Texas at Austin Antti Tolli; University of Oulu Robert Heath; University of Texas at Austin Upamanyu Madhow; University of California, Santa Barbara </details> * MP2b: Distributed Optimization in Networked Settings (Invited) Surf & Sand <details> <summary> Details </summary> MP2b-1: STOCHASTIC ZEROTH-ORDER ALGORITHM FOR DECENTRALIZED NONCONVEX OPTIMIZATION WITH OPTIMAL NETWORK SCALING Haoran Sun; University of Minnesota Mingyi Hong; University of Minnesota MP2b-2: ON MAINTAINING LINEAR CONVERGENCE OF DISTRIBUTED LEARNING AND OPTIMIZATION UNDER LIMITED COMMUNICATION Sindri Magnusson; KTH Royal Institute of Technology Hossein Shokri-Ghadikolaei; KTH Royal Institute of Technology Na Li; Harvard University MP2b-3: CONVERGENCE OF ASYNCHRONOUS SUBGRADIENT PUSH UNDER ARBITRARY BOUNDED DELAYS Mahmoud Assran; McGill University/Facebook Michael Rabbat; Facebook MP2b-4: DISTRIBUTED INFERENCE OVER NETWORKS: GEOMETRICALLY CONVERGENT ALGORITHMS AND STATISTICAL GUARANTEES Ying Sun; Purdue University Ye Tian; Purdue University Gesualdo Scutari; Purdue University Guang Cheng; Purdue University </details> * MP3b: Tensor Modeling and Processing (Invited) Triton <details> <summary> Details </summary> MP3b-1: LOW MULTILINEAR RANK UPDATING Stijn Hendrikx; KU Leuven Michiel Vandecappelle; KU Leuven Lieven De Lathauwer; KU Leuven MP3b-2: ON THE ROLE OF SAMPLING IN UNDERDETERMINED TENSOR DECOMPOSITION WITH KRONECKER AND KHATRI-RAO STRUCTURED FACTORS Mehmet Can Hucumenoglu; University of California, San Diego Piya Pal; University of California, San Diego MP3b-3: TENSOR-BASED LOCALIZATION OF NON-STATIONARY BRAIN SOURCES Nasrin Taheri; LTSI - UMR 1099, F-35000 Rennes Amar Kachenoura; LTSI - UMR 1099, F-35000 Rennes Ahmad Karfoul; LTSI - UMR 1099, F-35000 Rennes Karim Ansari; Université Shahid Chamran d'Ahvaz Lotfi Senhadi; LTSI - UMR 1099, F-35000 Rennes Laurent Albera; LTSI - UMR 1099, F-35000 Rennes MP3b-4: CHANNEL ESTIMATION FOR TENSOR MIMO OFDM IN THE MILLIMETER WAVE BAND Damir Rakhimov; Ilmenau University of Technology Jianshu Zhang; Ilmenau University of Technology Andre de Almeida; Federal University of Ceara Adel Nadeev; Kazan National Research Technical University Martin Haardt; Ilmenau University of Technology </details> * MP4b: Geometric Deep Learning 2 (Invited) Heather <details> <summary> Details </summary> MP4b-1: CONVOLUTIONAL GRAPH NEURAL NETWORKS Fernando Gama; University of Pennsylvania Antonio Marques; King Juan Carlos University Geert Leus; Delft University of Technology Alejandro Ribeiro; University of Pennsylvania MP4b-2: CONVOLUTION AND SAMPLING IN GRAPH SIGNAL PROCESSING John Shi; Carnegie Mellon University Jose Moura; Carnegie Mellon University MP4b-3: POOLING IN GRAPH CONVOLUTIONAL NEURAL NETWORKS Mark Cheung; Carnegie Mellon University John Shi; Carnegie Mellon University Oren Wright; Carnegie Mellon University Yao Jiang; Carnegie Mellon University Jose Moura; Carnegie Mellon University MP4b-4: FAST GRAPH CONVOLUTIONAL RECURRENT NETWORKS Sai Kiran Kadambari; Indian Institute of Science Sundeep Prabhakar Chepuri; Indian Institute of Science </details> * MP5b: Advances in Bayesian Machine Learning (Invited) Scripps <details> <summary> Details </summary> MP5b-1: DETECTING CAUSALITY USING DEEP GAUSSIAN PROCESSES Guanchao Feng; Stony Brook University J. Gerald Quirk; Stony Brook University Petar Djuric; Stony Brook University MP5b-2: APPROXIMATE SHANNON SAMPLING IN IMPORTANCE SAMPLING: NEARLY CONSISTENT FINITE PARTICLE APPROXIMATIONS Amrit Singh Bedi; US Army Research Laboratory Alec Koppel; US Army Research Laboratory Brian Sadler; US Army Research Laboratory Victor Elvira; IMT Lille Douai MP5b-3: LEARNING GAUSSIAN PROCESSES WITH BAYESIAN POSTERIOR OPTIMIZATION Luiz Chamon; University of Pennsylvania Santiago Paternain; University of Pennsylvania Alejandro Ribeiro; University of Pennsylvania MP5b-4: INFERENCE AND MODELLING FOR ASYMMETRIC HEAVY-TAILED STOCHASTIC PROCESSES Simon Godsill; University of Cambridge Marina Riabiz; University of Cambridge Ioannis Kontoyiannis; University of Cambridge </details> * MP6b: Neuromorphic Computing (Invited) Toyon <details> <summary> Details </summary> MP6b-1: THE PROMISE AND PITFALLS OF DEEP LEARNING WITH NON-VOLATILE MEMORY Pritish Narayanan; IBM Research - Almaden Stefano Ambrogio; IBM Research - Almaden Charles Mackin; IBM Research - Almaden Hsinyu Tsai; IBM Research - Almaden Geoffrey Burr; IBM Research - Almaden MP6b-2: EFFECT OF ASYMMETRIC NONLINEARITY DYNAMICS IN RRAMS ON SPIKING NEURAL NETWORK PERFORMANCE Mohammed Fouda; University of California, Irvine Emre Neftci; University of California, Irvine Ahmed Eltawil; University of California, Irvine Fadi Kurdahi; University of California, Irvine MP6b-3: SUPERVISED LEARNING WITH SPIKING NEURAL NETWORKS Bipin Rajendran; New Jersey Institute of Technology MP6b-4: SCALABLE NEUROMORPHIC DRAM-BASED CNN AND RNN ACCELERATORS Tobi Delbruck; University of Zurich / ETH Zurich Shih-Chii Liu; University of Zurich / ETH Zurich </details> * MP7b: Geometric and Topological Methods (Invited) Acacia <details> <summary> Details </summary> MP7b-1: ESTIMATION OF SPARSELY OBSERVED SIGNALS WITH AN EMPIRICAL BAYESIAN MODEL James Matuk; Ohio State University Oksana Chkrebtii; Ohio State University Sebastian Kurtek; Ohio State University MP7b-2: SHAPE MORPHING FOR ANALYSIS: AN OPTIMAL TRANSPORT APPROACH Aniruddha Adiga; North Carolina State University Ashkan Panahi; North Carolina State University Wen Tang; North Carolina State University Hamid Krim; North Carolina State University MP7b-3: A WEIGHT METAMORPHOSIS MODEL FOR REGISTRATION OF UNBALANCED SHAPES. Nicolas Charon; Johns Hopkins University MP7b-4: APPROXIMATE LOG-DETERMINANT DIVERGENCES BETWEEN COVARIANCE OPERATORS AND APPLICATIONS Minh Ha Quang; RIKEN Center for Advanced Intelligence Project </details> #### 18:30 - 21:30 Conference Cocktail/Social - *The Cocktail/Social takes the place of Monday’s dinner. No charge for conference attendees and a guest.* (Merrill Hall)