Timezone: »
The replica method is a non-rigorous but widely-used technique from statistical physics used in the asymptotic analysis of many large random nonlinear problems. This paper applies the replica method to non-Gaussian MAP estimation. It is shown that with large random linear measurements and Gaussian noise, the asymptotic behavior of the MAP estimate of an n-dimensional vector ``decouples as n scalar MAP estimators. The result is a counterpart to Guo and Verdus replica analysis on MMSE estimation. The replica MAP analysis can be readily applied to many estimators used in compressed sensing, including basis pursuit, lasso, linear estimation with thresholding and zero-norm estimation. In the case of lasso estimation, the scalar estimator reduces to a soft-thresholding operator and for zero-norm estimation it reduces to a hard-threshold. Among other benefits, the replica method provides a computationally tractable method for exactly computing various performance metrics including MSE and sparsity recovery.
Author Information
Sundeep Rangan (Qualcomm)
Alyson Fletcher (UCLA)
Vivek K Goyal (Massachusetts Institute of Technology)
Related Events (a corresponding poster, oral, or spotlight)
-
2009 Poster: Asymptotic Analysis of MAP Estimation via the Replica Method and Compressed Sensing »
Tue. Dec 8th 03:00 -- 07:59 AM Room
More from the Same Authors
-
2022 Poster: Instability and Local Minima in GAN Training with Kernel Discriminators »
Evan Becker · Parthe Pandit · Sundeep Rangan · Alyson Fletcher -
2019 Poster: Input-Output Equivalence of Unitary and Contractive RNNs »
Melikasadat Emami · Mojtaba Sahraee Ardakan · Sundeep Rangan · Alyson Fletcher -
2017 Poster: Rigorous Dynamics and Consistent Estimation in Arbitrarily Conditioned Linear Systems »
Alyson Fletcher · Mojtaba Sahraee-Ardakan · Sundeep Rangan · Philip Schniter -
2016 : From Brains to Bits and Back Again »
Yoshua Bengio · Terrence Sejnowski · Christos H Papadimitriou · Jakob H Macke · Demis Hassabis · Alyson Fletcher · Andreas Tolias · Jascha Sohl-Dickstein · Konrad P Koerding -
2016 : Welcome and Opening Remarks »
Alyson Fletcher · Konrad P Koerding -
2016 Workshop: Brains and Bits: Neuroscience meets Machine Learning »
Alyson Fletcher · Eva Dyer · Jascha Sohl-Dickstein · Joshua T Vogelstein · Konrad Koerding · Jakob H Macke -
2015 Workshop: Statistical Methods for Understanding Neural Systems »
Alyson Fletcher · Jakob H Macke · Ryan Adams · Jascha Sohl-Dickstein -
2014 Poster: Scalable Inference for Neuronal Connectivity from Calcium Imaging »
Alyson Fletcher · Sundeep Rangan -
2014 Spotlight: Scalable Inference for Neuronal Connectivity from Calcium Imaging »
Alyson Fletcher · Sundeep Rangan -
2013 Workshop: High-dimensional Statistical Inference in the Brain »
Alyson Fletcher · Dmitri B Chklovskii · Fritz Sommer · Ian H Stevenson -
2012 Poster: Approximate Message Passing with Consistent Parameter Estimation and Applications to Sparse Learning »
Ulugbek S Kamilov · Sundeep Rangan · Alyson Fletcher · MIchael Unser -
2011 Poster: Neural Reconstruction with Approximate Message Passing (NeuRAMP) »
Alyson Fletcher · Sundeep Rangan · Lav R Varshney · Aniruddha Bhargava -
2009 Poster: Orthogonal Matching Pursuit From Noisy Random Measurements: A New Analysis »
Alyson Fletcher · Sundeep Rangan -
2009 Spotlight: Orthogonal Matching Pursuit From Noisy Random Measurements: A New Analysis »
Alyson Fletcher · Sundeep Rangan -
2008 Poster: Resolution Limits of Sparse Coding in High Dimensions »
Alyson Fletcher · Sundeep Rangan · Vivek K Goyal