← All authors Martin J. Wainwright Massachusetts Institute of Technology (from arXiv:2401.13665, 2024) · ORCID · OpenAlex
113 papers in scope · 110 published · 3 on the econ.EM arXiv · 15,617 citations · h-index 50 (over the papers listed here)
Related authors The 20 authors closest to this one in our weighted citation graph, most related first.
Stephen Bates Feng Shi Pascal Michaillat Ravi Jagadeesan Ercument Cahan Paul Niehaus Jungjun Choi Guanhao Zhou Xiufan Yu Ming Yuan Jushan Bai Adam McCloskey Serena Ng Munther A. Dahleh Dennis Shen Brad Ross Davide Viviano Anish Agarwal Yuefeng Han Devavrat Shah Proximity is measured over citations between two papers we both hold, weighted by how heavily one leans on the other, and is symmetric — it does not distinguish citing from being cited. Authors without a profile here are skipped, and a genuinely close colleague can be missing simply because their work is not in our arXiv corpus. Method: docs/06-citations-pipeline.md .
Papers (3 of 113)
Near-optimal inference in adaptive linear regression
published 2025 · The Annals of Statistics · 5 citations
working paper 2025 · arXiv
Semiparametric inference based on adaptively collected data
published 2025 · The Annals of Statistics
working paper 2024 · arXiv
Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints
published 2024 · The Annals of Statistics · 2 citations · first circulated 2023
with Reese Pathak, Lin Xiao
Optimal policy evaluation using kernel-based temporal difference methods
published 2024 · The Annals of Statistics · 4 citations · first circulated 2021
Instance-Optimality in Optimal Value Estimation: Adaptivity via Variance-Reduced Q -Learning
published 2024 · IEEE Transactions on Information Theory · 2 citations · first circulated 2021
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
published 2024 · Mathematical Statistics and Learning · 4 citations · first circulated 2021
with Wenlong Mou, Ashwin Pananjady, Peter L. Bartlett
working paper 2024 · arXiv · 2 citations
Optimally tackling covariate shift in RKHS-based nonparametric regression
published 2023 · The Annals of Statistics · 18 citations · first circulated 2022
with Cong Ma, Reese Pathak
Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing
published 2023 · Management Science · 3 citations
Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity
published 2022 · Bernoulli · 37 citations · first circulated 2019
with Wenlong Mou, Nicolas Flammarion, Peter L. Bartlett
Minimax Off-Policy Evaluation for Multi-Armed Bandits
published 2022 · IEEE Transactions on Information Theory · 4 citations · first circulated 2021
with Cong Ma, Banghua Zhu, Jiantao Jiao
A Permutation-Based Model for Crowd Labeling: Optimal Estimation and Robustness
published 2020 · IEEE Transactions on Information Theory · 44 citations
Singularity, misspecification and the convergence rate of EM
published 2020 · The Annals of Statistics · 40 citations · first circulated 2018
Towards optimal estimation of bivariate isotonic matrices with unknown permutations
published 2020 · The Annals of Statistics · 10 citations · first circulated 2018
with Cheng Mao, Ashwin Pananjady
Instance-Dependent ℓ ∞ -Bounds for Policy Evaluation in Tabular Reinforcement Learning
published 2020 · IEEE Transactions on Information Theory · 24 citations · first circulated 2019
with Ashwin Pananjady
On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration
published 2020 · Conference on Learning Theory · 21 citations
Worst-case versus average-case design for estimation from partial pairwise comparisons
published 2020 · The Annals of Statistics · 12 citations
with Ashwin Pananjady, Cheng Mao, Vidya Muthukumar, Thomas A. Courtade
The Local Geometry of Testing in Ellipses: Tight Control via Localized Kolmogorov Widths
published 2020 · IEEE Transactions on Information Theory · 13 citations · first circulated 2017
with Yuting Wei
From Gauss to Kolmogorov: Localized measures of complexity for ellipses
published 2020 · Electronic Journal of Statistics · 4 citations · first circulated 2018
with Yuting Wei, Billy Fang
Active ranking from pairwise comparisons and when parametric assumptions do not help
published 2019 · The Annals of Statistics · 50 citations · first circulated 2016
A unified treatment of multiple testing with prior knowledge using the p-filter
published 2019 · The Annals of Statistics · 21 citations · first circulated 2017
Early Stopping for Kernel Boosting Algorithms: A General Analysis With Localized Complexities
published 2019 · IEEE Transactions on Information Theory · 23 citations · first circulated 2017
with Yuting Wei, Fanny Yang
Function-Specific Mixing Times and Concentration Away from Equilibrium
published 2019 · Bayesian Analysis · 1 citations
The geometry of hypothesis testing over convex cones: Generalized likelihood ratio tests and minimax radii
published 2019 · The Annals of Statistics · 15 citations · first circulated 2017
with Yuting Wei, Adityanand Guntuboyina
A sequential algorithm for false discovery rate control on directed acyclic graphs
published 2018 · Biometrika · 21 citations
Optimal Rates and Tradeoffs in Multiple Testing
published 2018 · Statistica Sinica · 6 citations
Log-concave sampling: Metropolis-Hastings algorithms are fast
published 2018 · Conference on Learning Theory · 89 citations
Convergence guarantees for a class of non-convex and non-smooth optimization problems
published 2018 · International Conference on Machine Learning · 37 citations
with Koulik Khamaru
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate
published 2018 · International Conference on Machine Learning · 21 citations
Statistical Recovery of Discrete, Geometric and Invariant Structures
published 2018 · Oberwolfach Reports
Rejoinder
published 2018 · Journal of the American Statistical Association
Theoretical guarantees for EM under misspecified Gaussian mixture models
published 2018 · Neural Information Processing Systems · 10 citations
no link
On kernel methods for covariates that are rankings
published 2018 · Electronic Journal of Statistics
Kernel feature selection via conditional covariance minimization
published 2017 · Neural Information Processing Systems · 56 citations
Support recovery without incoherence: A case for nonconvex regularization
published 2017 · The Annals of Statistics · 4 citations · first circulated 2014
with Po-Ling Loh
Linear Regression With Shuffled Data: Statistical and Computational Limits of Permutation Recovery
published 2017 · IEEE Transactions on Information Theory · 96 citations
with Ashwin Pananjady, Thomas A. Courtade
Minimax Optimal Procedures for Locally Private Estimation
published 2017 · Journal of the American Statistical Association · 24 citations
Convexified convolutional neural networks
published 2017 · International Conference on Machine Learning · 20 citations · first circulated 2016
with Yuchen Zhang, Percy Liang
On Concentration for (Regularized) Empirical Risk Minimization
published 2017 · Sankhya A · 19 citations
with Sara van de Geer
Rejoinder
published 2017 · Sankhya A
with Sara van de Geer
A framework for Multi-A(rmed)/B(andit) Testing with Online FDR Control
published 2017 · Neural Information Processing Systems · 17 citations
Randomized sketches for kernels: Fast and optimal nonparametric regression
published 2017 · The Annals of Statistics · 148 citations
with Yun Yang, Mert Pilancı
Statistical guarantees for the EM algorithm: From population to sample-based analysis
published 2017 · The Annals of Statistics · 400 citations · first circulated 2014
with Sivaraman Balakrishnan, Bin Yu
Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators
published 2017 · Electronic Journal of Statistics · 38 citations · first circulated 2015
More powerful and flexible rules for online FDR control with memory and weights
published 2017 · Neural Information Processing Systems
no link
Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues
published 2016 · IEEE Transactions on Information Theory · 13 citations · first circulated 2015
On the computational complexity of high-dimensional Bayesian variable selection
published 2016 · The Annals of Statistics · 138 citations · first circulated 2015
Asymptotic behavior of $\ell_p$-based Laplacian regularization in semi-supervised learning
published 2016 · Conference on Learning Theory · 24 citations
A practical scheme and fast algorithm to tune the lasso with optimality guarantees
published 2016 · Journal of Machine Learning Research · 36 citations · first circulated 2014
Simple, Robust and Optimal Ranking from Pairwise Comparisons
published 2015 · Journal of Machine Learning Research · 72 citations
The geometry of kernelized spectral clustering
published 2015 · The Annals of Statistics · 55 citations
with Geoffrey Schiebinger, Bin Yu
Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
published 2015 · IEEE Transactions on Information Theory · 388 citations · first circulated 2013
Structured Regularizers for High-Dimensional Problems: Statistical and Computational Issues
published 2014 · Annual Review of Statistics and Its Application · 114 citations
Using machine learning for discovery in synoptic survey imaging data
published 2013 · Monthly Notices of the Royal Astronomical Society · 122 citations
with Henrik Brink, Joseph W. Richards, D. Poznanski, J. S. Bloom, John Rice, Sahand Negahban
Divide and Conquer Kernel Ridge Regression
published 2013 · Conference on Learning Theory · 301 citations
with Yuchen Zhang, John C. Duchi
Communication-efficient algorithms for statistical optimization
published 2013 · Journal of Machine Learning Research · 213 citations · first circulated 2012
with Yuchen Zhang, John C. Duchi
Stochastic Belief Propagation: A Low-Complexity Alternative to the Sum-Product Algorithm
published 2012 · IEEE Transactions on Information Theory · 45 citations · first circulated 2011
with Nima Noorshams
Finite Sample Convergence Rates of Zero-Order Stochastic Optimization Methods
published 2012 · Neural Information Processing Systems · 27 citations
no link
A Unified Framework for High-Dimensional Analysis of $M$-Estimators with Decomposable Regularizers
published 2012 · Statistical Science · 301 citations
with Sahand Negahban, Pradeep Ravikumar, Bin Yu
Fast global convergence of gradient methods for high-dimensional statistical recovery
published 2012 · The Annals of Statistics · 212 citations · first circulated 2010
with Alekh Agarwal, Sahand Negahban
Sampled forms of functional PCA in reproducing kernel Hilbert spaces
published 2012 · The Annals of Statistics · 25 citations
with Arash Amini
Discussion: Latent variable graphical model selection via convex optimization
published 2012 · The Annals of Statistics · 15 citations
High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
published 2012 · The Annals of Statistics · 556 citations · first circulated 2011
with Po-Ling Loh
Information-Theoretic Limits of Selecting Binary Graphical Models in High Dimensions
published 2012 · IEEE Transactions on Information Theory · 205 citations · first circulated 2009
with Narayana Santhanam
Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
published 2012 · IEEE Transactions on Information Theory · 237 citations · first circulated 2009
with Alekh Agarwal, Peter L. Bartlett, Pradeep Ravikumar
No voodoo here! Learning discrete graphical models via inverse covariance estimation
published 2012 · Neural Information Processing Systems · 1 citations
no link
Approximation properties of certain operator-induced norms on Hilbert spaces
published 2011 · Journal of Approximation Theory · 2 citations
with Arash Amini
Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
published 2011 · IEEE Transactions on Information Theory · 485 citations · first circulated 2009
with Garvesh Raskutti, Bin Yu
Simultaneous Support Recovery in High Dimensions: Benefits and Perils of Block $\ell _{1}/\ell _{\infty} $-Regularization
published 2011 · IEEE Transactions on Information Theory · 114 citations · first circulated 2009
with Sahand Negahban
Estimation of (near) low-rank matrices with noise and high-dimensional scaling
published 2011 · The Annals of Statistics · 580 citations · first circulated 2009
with Sahand Negahban
High-dimensional covariance estimation by minimizing ℓ1-penalized log-determinant divergence
published 2011 · Electronic Journal of Statistics · 794 citations · first circulated 2008
with Pradeep Ravikumar, Garvesh Raskutti, Bin Yu
Distributed Dual Averaging In Networks
published 2010 · Neural Information Processing Systems · 63 citations
with Alekh Agarwal, John C. Duchi
no link
Support union recovery in high-dimensional multivariate regression
published 2010 · The Annals of Statistics · 367 citations · first circulated 2008
Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
published 2010 · IEEE Transactions on Information Theory · 674 citations · first circulated 2007
Major Advances and Emerging Developments of Graphical Models [From the Guest Editors]
published 2010 · IEEE Signal Processing Magazine · 15 citations
Network-Based Consensus Averaging With General Noisy Channels
published 2010 · IEEE Transactions on Signal Processing · 79 citations · first circulated 2008
with Ram Rajagopal
Network Coding for Distributed Storage Systems
published 2010 · IEEE Transactions on Information Theory · 1989 citations · first circulated 2007
with Alexandros G. Dimakis, P. Brighten Godfrey, Yunnan Wu, Kannan Ramchandran
Information-Theoretic Limits on Sparse Signal Recovery: Dense versus Sparse Measurement Matrices
published 2010 · IEEE Transactions on Information Theory · 171 citations · first circulated 2008
with Wei Wang, Kannan Ramchandran
Lossy Source Compression Using Low-Density Generator Matrix Codes: Analysis and Algorithms
published 2010 · IEEE Transactions on Information Theory · 80 citations
with Elitza Maneva, Emin Martinian
Analysis of Absorbing Sets and Fully Absorbing Sets of Array-Based LDPC Codes
published 2010 · IEEE Transactions on Information Theory · 214 citations · first circulated 2007
with Lara Dolecek, Zhengya Zhang, Venkat Anantharam, Borivoje Nikolić
Lower bounds on minimax rates for nonparametric regression with additive sparsity and smoothness
published 2009 · Neural Information Processing Systems · 16 citations
with Garvesh Raskutti, Bin Yu
no link
Information-Theoretic Limits on Sparsity Recovery in the High-Dimensional and Noisy Setting
published 2009 · IEEE Transactions on Information Theory · 438 citations · first circulated 2007
Guessing Facets: Polytope Structure and Improved LP Decoder
published 2009 · IEEE Transactions on Information Theory · 41 citations · first circulated 2006
with Alexandros G. Dimakis, Amin Gohari
Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
published 2009 · IEEE Transactions on Information Theory · 1258 citations · first circulated 2006
Low-Density Graph Codes That Are Optimal for Binning and Coding With Side Information
published 2009 · IEEE Transactions on Information Theory · 49 citations
with Emin Martinian
Model Selection in Gaussian Graphical Models: High-Dimensional Consistency of boldmathell_1-regularized MLE
published 2008 · Neural Information Processing Systems · 113 citations
with Garvesh Raskutti, Bin Yu, Pradeep Ravikumar
no link
Convergence Analysis of Reweighted Sum-Product Algorithms
published 2008 · IEEE Transactions on Signal Processing · 48 citations · first circulated 2007
with Tanya Roosta, S. Shankar Sastry
Probabilistic Analysis of Linear Programming Decoding
published 2008 · IEEE Transactions on Information Theory · 76 citations · first circulated 2007
On Optimal Quantization Rules for Some Problems in Sequential Decentralized Detection
published 2008 · IEEE Transactions on Information Theory · 9 citations
Geographic Gossip: Efficient Averaging for Sensor Networks
published 2008 · IEEE Transactions on Signal Processing · 192 citations · first circulated 2006
with Alexandros D. G. Dimakis, Anand D. Sarwate, Alexandros G. Dimakis
Phase transitions for high-dimensional joint support recovery
published 2008 · Neural Information Processing Systems · 17 citations
with Sahand Negahban
no link
Loop Series and Bethe Variational Bounds in Attractive Graphical Models
published 2007 · Neural Information Processing Systems · 63 citations
with Alan S. Willsky, Erik B. Sudderth
no link
Sparse Graph Codes for Side Information and Binning
published 2007 · IEEE Signal Processing Magazine · 33 citations
A new look at survey propagation and its generalizations
published 2007 · Journal of the ACM · 140 citations · first circulated 2004
with Elitza Maneva, Elchanan Mossel, Eliza N. Maneva
LP Decoding Corrects a Constant Fraction of Errors
published 2007 · IEEE Transactions on Information Theory · 121 citations · first circulated 2004
with Jon Feldman, Tal Malkin, Rocco A. Servedio, Clifford Stein
High-Dimensional Graphical Model Selection Using ell_1-Regularized Logistic Regression
published 2006 · Neural Information Processing Systems · 182 citations
with John Lafferty, Pradeep Ravikumar
Estimating the Wrong Graphical Model: Benefits in the Computation-Limited Setting
published 2006 · Journal of Machine Learning Research · 95 citations
Distributed fusion in sensor networks
published 2006 · IEEE Signal Processing Magazine · 205 citations
with Müjdat Çetin, Lei Chen, John W. Fisher, Alexander Ihler, Randolph L. Moses, Alan S. Willsky
Log-determinant relaxation for approximate inference in discrete Markov random fields
published 2006 · IEEE Transactions on Signal Processing · 99 citations
Data association based on optimization in graphical models with application to sensor networks
published 2006 · Mathematical and Computer Modelling · 77 citations
with Lei Chen, Müjdat Çetin, Alan S. Willsky
Divergences, surrogate loss functions and experimental design
published 2005 · Neural Information Processing Systems · 7 citations
no link
MAP Estimation Via Agreement on Trees: Message-Passing and Linear Programming
published 2005 · IEEE Transactions on Information Theory · 674 citations
with Tommi Jaakkola, Alan S. Willsky
Nonparametric decentralized detection using kernel methods
published 2005 · IEEE Transactions on Signal Processing · 77 citations
A New Class of Upper Bounds on the Log Partition Function
published 2005 · IEEE Transactions on Information Theory · 404 citations
with Tommi Jaakkola, Alan S. Willsky
Using Linear Programming to Decode Binary Linear Codes
published 2005 · IEEE Transactions on Information Theory · 593 citations
with Jon Feldman, David R. Karger
Embedded Trees: Estimation of Gaussian Processes on Graphs with Cycles
published 2004 · IEEE Transactions on Signal Processing · 81 citations
with Erik B. Sudderth, Alan S. Willsky
Tree consistency and bounds on the performance of the max-product algorithm and its generalizations
published 2004 · Statistics and Computing · 133 citations
with Tommi Jaakkola, Alan S. Willsky
Semidefinite Relaxations for Approximate Inference on Graphs with Cycles
published 2003 · Neural Information Processing Systems · 26 citations
no link
Tree-based reparameterization framework for analysis of sum-product and related algorithms
published 2003 · IEEE Transactions on Information Theory · 241 citations
with Tommi Jaakkola, Alan S. Willsky
Statistical and Information-Theoretic Methods for Self-Organization and Fusion of Multimodal, Networked Sensors
published 2002 · The International Journal of High Performance Computing Applications · 12 citations
with John W. Fisher, Erik B. Sudderth, Alan S. Willsky
Scale mixtures of Graussians and the statistics of natural images
published 2000 · Neural Information Processing Systems · 5 citations
with Eero P. Simoncelli
no link
Assembled from arXiv and OpenAlex. Duplicate records for the same paper are merged, and the published version is shown where we could identify one. Corrections welcome.
Built from arXiv and OpenAlex. Supported by UKRI grant APP47921 (Martin Weidner, UCL · Francis J. DiTraglia, Oxford).