As I was reading this presentation Universal Denoising and Approximate Message Passing by Dror Baron , Yanting Ma and Junan Zhu, I realized I had not covered the ITA conference yet.
Here are some of the abstracts of the presentations made there, some of which have been covered here on Nuit Blanche already. Enjoy !
Zhu
- Capacity-Approaching Sparse-Graph Code for Compressive Phase Retrieval Ramtin Pedarsani, UC Berkeley; Kangwook Lee, UC Berkeley; Kannan Ramchandran*, UC Berkeley
Finding globally optimal k-means clusterings through convex relaxation Rachel Ward*, UT Austin
- Limits on Support Recovery with Probabilistic Models: An Information-Spectrum Approach Jonathan Scarlett*, EPFL; Volkan Cevher, EPFL
- Locating outliers in large matrices with adaptive compressive sampling Xingguo Li, University Of Minnesota; Jarvis Haupt*, University Of Minnesota
- Compressive modeling of stationary autoregressive processes Georg Kail, Delft University Of Technology; Geert Leus*, Delft University Of Technology
- The benefits of nonconvex optimization for compressed sensing, Galen Reeves*, Duke
- A totally unimodular view of structured sparsity Volkan Cevher*, Swiss Federal Institute of Technology in Lausanne
- Stable Super-Resolution of Positive Sources Veniamin Morgenshtern*, Stanford; Emmanuel Candes, Stanford
-
- Doubly sparse compressed sensing Grigory Kabatiansky*, IITP RAS; Serge Vladuts, Aix-Marseille University, France; Cedric Tavernier, Assystem, France
- Sub-linear Time Compressed Sensing using Sparse-Graph Codes, Xiao Li*, UC Berkeley; Sameer Pawar, UC Berkeley; Kannan Ramchandran, UC Berkeley
- Universal Denoising and Approximate Message Passing, Dror Baron*, NC State
- Universal compressed sensing of Markov sources Shirin Jalali*, Princeton; H. Vincent Poor, Princeton
- Generalized Compressive Interferometry for Optical Modal Analysis George Atia*, University of Central Florida; Ayman Abouraddy, University of Central Florida; Davood Mardani, University of Central Florida
- Optimal Data-Dependent Hashing for Nearest Neighbors Alexandr Andoni*, Simons Institute for the Theory of Computing, UC Berkeley; Ilya Razenshteyn, MIT
- Streaming and space efficient approximation algorithms for Subset Sum Anna Gal*, UT Austin; Jing-Tang Jang, Google; Nutan Limaye, IIT Bombay; Meena Mahajan, Institute of Mathematical Sciences Chennai; Karteek Sreenivasaiah, Max Planck Institute for Informatics
- Nearly optimal and deterministic sparse Hadamard transform Mahdi Cheraghchi*, UC Berkeley; Piotr Indyk, MIT
- On the stability of collaborative dictionary learning Waheed Bajwa*, Rutgers
- Learning Minimal Latent Directed Information Polytrees Negar Kiyavash*, UIUC
- Exploration-Exploitation: a low rank matrix completion solution and performance bounds Urbashi Mitra*, USC; Sunav Choudhary, USC
- Low-rank methods to address the big data issues in the synchrophasor measurements in the power system Meng Wang*, RPI; Pengzhi Gao, RPI; Joe H. Chow, RPI; Scott Ghiocel, RPI; Bruce Fardanesh, New York Power Authority; George Stefopoulos, New York Power Authority
- THE NETFLIX RECOMMENDER SYSTEM: WHAT IT IS AND HOW WE IMPROVE IT Carlos Gomez-Uribe*, Netflix, Inc.
- Optimal CUR Matrix Decompositions, Christos Boutsidis*, Yahoo; David Woodruff, IBM
- Single pass spectral sparsification in dynamic streams, Michael Kapralov*, IBM T.J Watson; Yin-Tat Lee, MIT; Cameron Musco, MIT; Christopher Musco, MIT; Aaron Sidford, MIT
- Sketching for M-Estimators: A Unified Approach to Robust Regression Ken Clarkson*, IBM Research - Almaden; David Woodruff, IBM Almaden
-
- Elementary estimators for high-dimensional statistical models Eunho Yang, IBM T.J Watson; Aurelie Lozano, IBM T.J Watson; Pradeep Ravikumar*, UT Austin
- Inference in High-Dimensional Varying Coefficient Models Mladen Kolar*, University Of Chicago; Damian Kozbur, ETH
- Stochastic Iterative Greedy Algorithms for Sparse Reconstruction Nam Nguyen, MIT; Deanna Needell*, Claremont McKenna College; Tina Woolf, Claremont Graduate University
- High dimensional variable selection: a decision theoretic approach Oluwasanmi Koyejo*, Stanford; Rajiv Khanna, University Of Texas; Joydeep Ghosh, University Of Texas; Russell Poldrack, Stanford
- Big Tensor Subspace Learning for Dynamic MRI Georgios B. Giannakis*, University Of Minnesota
- Clustering with Distributed Data: A Consensus+Innovations Approach Soummya Kar*, CMU
-
- Non-convex Robust PCA Praneeth Netrapalli, Microsoft Research; U. Niranjan, UC Irvine; Sujay Sanghavi*, UT Austin; Anima Anandkumar, UC Irvine; Prateek Jain, Microsoft Research
- Simple, Efficient and Neural Algorithms for Sparse Coding Ankur Moitra*, MIT
- Correlation decay, Phase transitions, and Counting Alistair Sinclair, UC Berkeley; Piyush Srivastava*, Caltech; Daniel Stefankovic, University Of Rochester; Yitong Yin, Nanjing University
- K-clustering of Semi-Random graphs, Alexandra Kolla*, UIUC
- Incremental clustering: The case for extra clusters, Margareta Ackerman*, Florida State University; Sanjoy Dasgupta, UC San Diego
- The Lovász Local Lemma as a Random Walk, Dimitris Achlioptas*, UC Santa Cruz; Fotis Iliopoulos, UC Berkeley
- Inverse Rendering using Color+Depth Camera, Ha Nguyen, EPFL; Minh Do*, University Of Illinois
- Environmental information from noise, Peter Gerstoft*, UC San Diego
- Clustering techniques applied to the human seismic footprint, Nima Riahi*, UC San Diego; Peter Gerstoft, UC San Diego
- Earthquake Ground Motion Prediction using Seismic Noise, Marine Denolle*, UC San Diego
- Parametric Bilinear Generalized Approximate Message Passing, Phil Schniter*, Ohio State; Jason Parker, AFRL
- Capacity-achieving sparse regression codes via approximate message passing decoding Cynthia Rush, Yale; Adam Greig, Cambridge; Ramji Venkataramanan*, Cambridge
- Algorithms for Parameter Estimation in Mixture Models, Aditya Bhaskara*, Google
- Control-based analog-to-digital conversion without sampling and quantization, Hans-Andrea Loeliger*, ETH; Georg Wilckens, ETH
- Sub-Nyquist Detection and Estimation Using Equivalent-time Sampling, Tarig Ballal, King Abdullah University of Science and Technology ; Tareq Al-Naffouri*, King Abdullah University of Science and Technology
- Estimation with Norm Regularization, Arindam Banerjee*, University Of Minnesota; Sheng Chen, University Of Minnesota; Farideh Fazayeli, University Of Minnesota; Vidyashankar Sivakumar, University Of Minnesota
- Learning Probability Distributions over Structured Spaces, Arthur Choi, UC Los Angeles; Guy Van den Broeck, KU Leuven; Adnan Darwiche*, UC Los Angeles
- Polar codes for the broadcast channel with confidential messages and constrained randomization, Rémi Chou, Georgia Tech; Matthieu Bloch*, Georgia Tech
- Pipelining for Accuracy in Randomized Digital Computation, Marc Riedel*, University Of Minnesota
- Learning from pairwise comparisons, Mark Davenport*, Georgia Tech
- See-Through Imaging and Occupancy Estimation with RF Signals, Yasamin Mostofi*, UC Santa Barbara
- Clustering multi-way data: A novel algebraic approach Eric Kernfeld, University Of Washington; Misha Kilmer, Tufts University; Shuchin Aeron*, Tufts University
- A graph sampling perspective for semi-supervised learning Aly El Gamal*, USC; Aamir Anis, USC; Salman Avestimehr, USC; Antonio Ortega, USC
- Stochastic Iterative Greedy Algorithms for Sparse Reconstruction, Nam Nguyen, MIT; Deanna Needell*, Claremont McKenna College; Tina Woolf, Claremont Graduate University
- High dimensional variable selection: a decision theoretic approach, Oluwasanmi Koyejo*, Stanford; Rajiv Khanna, University Of Texas; Joydeep Ghosh, University Of Texas; Russell Poldrack, Stanford
- Elementary estimators for high-dimensional statistical models Eunho Yang, IBM T.J Watson; Aurelie Lozano, IBM T.J Watson; Pradeep Ravikumar*, UT Austin
- Inference in High-Dimensional Varying Coefficient Models, Mladen Kolar*, University Of Chicago; Damian Kozbur, ETH
- Landmarking Manifolds with Gaussian Processes, John Paisley*, Columbia
- Learning in Repeated Auctions Kareem Amin, UPenn; Afshin Rostamizadeh*, Google; Umar Syed, Google
- Machine Learning in Apache Spark Ameet Talwalkar*, UC Los Angeles
-
- Subspace Clustering with Ordered Weighted L1 minimization Ulas Ayaz*, Brown University
- Pessimistic active learning using robust bias-aware prediction Anqi Liu, University Of Illinois Chicago; Lev Reyzin*, University Of Illinois Chicago; Brian Ziebart, University Of Illinois Chicago
Here are some videos presentations of some of the talks:
- Interference in finite-sized highly dense millimeter wave networks, Kiran Venugopal, UT Austin Matthew Valenti, West Virginia University Robert Heath, UT Austin
- Information guided sequential compressed sensing, Yao Xie, Georgia Tech
- A Reusable Holdout for Guaranteed Classifier Validation, Moritz Hardt, IBM Research - Almaden
- Unified scaling of polar codes: error exponent, scaling exponent, moderate deviations, and error floors, Marco Mondelli, EPFL Seyed Hamed Hassani, ETH Ruediger Urbanke, EPFL
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email, explore the Big Picture in Compressive Sensing or the Matrix Factorization Jungle and join the conversations on compressive sensing, advanced matrix factorization and calibration issues on Linkedin.
No comments:
Post a Comment