Noisy and Missing Data Regression: Distribution-Oblivious Support Recovery

Keywords

Noise (video), Minimax, Covariance, Computer science, Matching pursuit

References

• Corrupted and missing predictors: Minimax bounds for high-dimensional linear regressionPo‐Ling Loh, Martin J. Wainwright — 2012
• Missing values: sparse inverse covariance estimation and an extension to sparse regressionNicolas Städler, Peter Bühlmann — 2009
• Sparse recovery under matrix uncertaintyMathieu Rosenbaum, Alexandre B. Tsybakov — 2008
• Stable recovery of sparse overcomplete representations in the presence of noiseDavid L. Donoho, Michael Elad, Vladimir Temlyakov — 2006
• High-dimensional regression with noisy and missing data: Provable guarantees with non-convexityPo‐Ling Loh, Martin J. Wainwright — 2011
• On Learning Discrete Graphical Models using Greedy MethodsAli Jalali, Christopher C. Johnson, Pradeep Ravikumar — 2011
• On the Impossibility of Uniform Sparse Reconstruction using Greedy MethodsHolger Rauhut — 2007
• Greed is good: algorithmic results for sparse approximationJoel A. Tropp — 2004
• Signal Recovery From Random Measurements Via Orthogonal Matching PursuitJoel A. Tropp, Anna C. Gilbert — 2007
• Analysis of Orthogonal Matching Pursuit Using the Restricted Isometry PropertyMark A. Davenport, Michael B. Wakin — 2009
• Orthogonal Matching Pursuit for Sparse Signal Recovery With NoiseTommaso Cai, Li-e Wang — 2011
• Model selection: Two fundamental measures of coherence and their algorithmic significanceWaheed U. Bajwa, Robert Calderbank, Sina Jafarpour — 2009
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over q -BallsGarvesh Raskutti, Martin J. Wainwright, Bin Yu — 2009
• Greedy Algorithms for Structurally Constrained High Dimensional ProblemsAmbuj Tewari, Pradeep Ravikumar, Inderjit S. Dhillon — 2011
• Measurement error in nonlinear models: a modern perspectiveRaymond J. Carroll, David Ruppert, Leonard A. Stefanski — 2006
• Festschrift for Lucien Le CamDavid Pollard, Erik Torgersen, Grace L. Yang — 1997
• Improved Matrix Uncertainty SelectorMathieu Rosenbaum, Alexandre B. Tsybakov — 2011
• Assouad, Fano, and Le CamBin Yu — 1997

Cited by

• Robust Sparse Regression under Adversarial CorruptionYudong Chen, Constantine Caramanis, Shie Mannor — 2013
• Measurement error in Lasso: impact and likelihood bias correctionØystein Sørensen, Arnoldo Frigessi, Magne Thoresen — 2012
• Robust High Dimensional Sparse Regression and Matching PursuitYudong Chen, Constantine Caramanis, Shie Mannor — 2013
• Learning with high-dimensional noisy dataYudong Chen — 2013
• Streaming Sparse Principal Component AnalysisWenzhuo Yang, Huan Xu — 2015
• Linear and conic programming estimators in high dimensional errors‐in‐variables modelsAlexandre Belloni, Mathieu Rosenbaum, Alexandre B. Tsybakov — 2014
• Distributed Robust LearningJiashi Feng, Huan Xu, Shie Mannor — 2014
• Sparse Recovery with Linear and Nonlinear Observations: Dependent and Noisy DataCem Aksoylar, Venkatesh Saligrama — 2014
• Sparse signal processing with linear and non-linear observations: A unified shannon theoretic approachCem Aksoylar, George Atia, Venkatesh Saligrama — 2013
• Robust Inverse Covariance Estimation under Noisy MeasurementsJun-Kun Wang, Shou-De Lin — 2014
• High dimensional errors-in-variables models with dependent measurementsMark Rudelson, Shuheng Zhou — 2015
• Information-Theoretic Characterization of Sparse RecoveryCem Aksoylar, Venkatesh Saligrama — 2014
• Universal Linear Fit Identification: A Method Independent of Data, Outliers and Noise Distribution Model and Free of Missing or Removed Data ImputationK. K. L. B. Adikaram, M. A. Hussein, Mathias Effenberger — 2015
• Covariate Selection in High-Dimensional Generalized Linear Models With Measurement ErrorØystein Sørensen, Kristoffer Herland Hellton, Arnoldo Frigessi — 2014
• Robust Elastic Net RegressionWeiyang Liu, Lin, Rongmei, Meng Yang — 2015
• High Dimensional Structured Estimation with Noisy DesignsAmir Asiaee T., Soumyadeep Chaterjee, Arindam Banerjee — 2016
• Abundant Inverse Regression using Sufficient Reduction and its ApplicationsHyunwoo J. Kim, Brandon M. Smith, Nagesh Adluru — 2016
• Low dimensional subspace finding via size-reducing dictionary learningBogdan Dumitrescu, Paul Irofti — 2016
• Errors-in-variables models with dependent measurementsMark Rudelson, Shuheng Zhou — 2016
• Outlier Robust Online LearningJiashi Feng, Huan Xu, Shie Mannor — 2017

Related papers

• High-dimensional regression with noisy and missing data: Provable guarantees with non-convexityPo‐Ling Loh, Martin J. Wainwright — 2011
• Sparse recovery under matrix uncertaintyMathieu Rosenbaum, Alexandre B. Tsybakov — 2008
• Regression Shrinkage and Selection via the LassoRobert Tibshirani — 1996
• SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTORPeter J. Bickel, Ya’acov Ritov, Alexandre B. Tsybakov — 2008
• Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using ℓ _1 -Constrained Quadratic Programming (Lasso)Martin J. Wainwright — 2009
• Measurement error in Lasso: impact and likelihood bias correctionØystein Sørensen, Arnoldo Frigessi, Magne Thoresen — 2012
• Compressed sensingDavid L. Donoho — 2006