High-dimensional testing

  • Y. Wei and M. J. Wainwright (2017). The local geometry of testing in ellipses: Tight control via localized Kolomogorov widths Arxiv pre-print, December 2017.

  • M. Rabinovich, A. Ramdas M. J. Wainwright, and M. I. Jordan (2017). Optimal Rates and Tradeoffs in Multiple Testing. Arxiv pre-print, May 2017.

  • A. Ramdas, R. Foygel Barber, M. J. Wainwright, and M. I. Jordan (2017). A Unified Treatment of Multiple Testing with Prior Knowledge. Arxiv pre-print, March 2017.

  • Y. Wei, A. Guntuboyina, and M. J. Wainwright (2017). The geometry of hypothesis testing over convex cones: Generalized likelihood tests and minimax radii. Arxiv pre-print, March 2017.

    Reinforcement learning

    D. Malik, A. Pananjady, K. Bhatia, K. Khamaru, P. L. Bartlett and M. J. Wainwright (2018). Derivative-free methods for policy optimization: Guarantees for linear-quadratic systems. Presented in part at the AISTATS 2019 Conference.

    Statistics and privacy

  • J. C. Duchi, M. I. Jordan and M. J. Wainwright (2013). Local privacy and minimax bounds: Sharp rates for probability estimation. Arxiv technical report, May 2013.

  • J. C. Duchi, M. I. Jordan and M. J. Wainwright (2013). Local privacy and statistical minimax rates. Arxiv technical report, February 2013.

  • J. C. Duchi, M. I. Jordan and M. J. Wainwright (2014). Privacy aware learning Journal of the ACM, Volume 61(6), November 2014. Presented in part at the NIPS Conference, December 2012.

    Sampling and Markov chains

  • R. Dwivedi, Y. Chen, M. J. Wainwright and B. Yu, TITLE = "Log-concave sampling: {M}etropolis-{H}astings algorithms are fast.", YEAR = 2018, ADDRESS = "Stockholm, Sweden", BOOKTITLE = "COLT: Conference on Computational Learning Theory

  • Y. Chen, R. Dwivedi, M. J. Wainwright and B. Yu (2018). Fast MCMC Sampling Algorithms on Polytopes Journal of Machine Learning Research, 19:1--86.

  • M. Rabinovich, A. Ramdas, M. I. Jordan, and M. J. Wainwright (2016) Function-Specific Mixing Times and Concentration Away from Equilibrium. Arxiv pre-print, May 2016.

  • Y. Yang, M. J. Wainwright and M. I. Jordan (2016) On the computational complexity of high-dimensional Bayesian variable selection. Annals of Statistics, 44(6): 2497---2532.

    High-dimensional estimation

  • P. Loh and M. J. Wainwright (2017). Support recovery without incoherence: A case for non-convex regularization. Annals of Statistics: 45(6): 2455--2482.

  • Y. Zhang, M. J. Wainwright and M. I. Jordan (2017). Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators. Electronic Journal of Statistics, 11: 752--799.

  • Y. Yang, M. J. Wainwright and M. I. Jordan (2016) On the computational complexity of high-dimensional Bayesian variable selection. Annals of Statistics, 44(6): 2497---2532.

  • P. Loh and M. J. Wainwright (2015). Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima. Journal of Machine Learning Research, 16:559--616, April 2015. Short version presented at NIPS conference, December 2013.

  • M. Pilanci, M. J. Wainwright and L. El Ghaoui (2015). Sparse learning via Boolean relaxation, Mathematical Programming, 151(1): 63--67. June 2015.

  • M. J. Wainwright (2014). Constrained forms of statistical minimax: Computation, communication and privacy. Proceedings of the International Congress of Mathematicians, Seoul, Korea. August 2014.

  • Y. Zhang, M. J. Wainwright and M. I. Jordan (2014). Lower bounds on the performance of polynomial-time algorithms for sparse linear regression. Short version appeared at COLT 2014 Conference, June 2014.

  • M. J. Wainwright (2014). Structured regularizers for high-dimensional problems: Statistical and computational issues. Annual Review of Statistics and its Applications, (1): 233--253.

  • J. C. Duchi and M. J. Wainwright (2013). Distance-based and continuum Fano inequalities with applications to statistical estimation. Arxiv pre-print, November 2013.

  • A. Agarwal, S. Negahban, and M. J. Wainwright (2012). Stochastic optimization and sparse statistical recovery: An optimal algorithm for high dimensions. Appeared at the NIPS Conference, December 2012, Lake Tahoe.

  • A. Agarwal, S. Negahban, and M. J. Wainwright (2012). Fast global convergence of gradient methods for high-dimensional statistical recovery. Annals of Statistics, 40(5):2452---2482.
  • Supplementary material (30 pages)
  • Preliminary versions:
  • Short version appeared at NIPS Conference, Vancouver, Canada. December 2010.
  • Arxiv paper posted April 2011.
  • S. Negahban, P. Ravikumar, M. J. Wainwright and B. Yu. (2012) A unified framework for high-dimensional analysis of M-estimators with decomposable regularizers. Statistical Science, 27(4): 538--557, December 2012.
  • Supplementary material only
  • Main body only
  • Short version appeared at NIPS Conference, Vancouver, Canada. December 2009.
  • P. Loh and M. J. Wainwright (2012). High-dimension regression with noisy and missing data: Provable guarantees with non-convexity. Annals of Statistics, 40(3): 1637--1664.
    Supplementary material (Appendices)
    Preliminary version: Presented part at NIPS Conference, Granada, Spain, December 2011.

  • A. Agarwal, S. Negahban, and M. J. Wainwright (2012). Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions. Annals of Statistics, 40(2):1171--1197.
  • Main section only (27 pages)
  • Supplementary material only (24 pages)
  • Preliminary versions:
  • International Conference on Machine Learning, June 2011.
  • Arxiv technical report, February 2011.
  • G. Raskutti, M. J. Wainwright and B. Yu (2012). Minimax-optimal rates for sparse additive models over kernel classes via convex programming. Journal of Machine Learning Research, 13:389--427. March 2012.
    Preliminary versions:
  • G. Raskutti, M. J. Wainwright and B. Yu. (2009) Lower bounds on minimax rates for nonparametric regression with additive smoothness and sparsity. NIPS paper. Appeared at the NIPS Conference, Vancouver, Canada. December 2009.
  • N. Santhanam and M. J. Wainwright (2012). Information-theoretic limits of selecting binary graphical models in high dimensions. IEEE Transactions on Information Theory, 58(7): 4117--4134, July 2012.
    Preliminary versions:
  • Presented at International Symposium on Information Theory (ISIT), Toronto, Canada. July, 2008.
  • Arxiv paper, May 2009.
  • M. Lopes, L. Jacob and M. J. Wainwright (2011). A More Powerful Two-Sample Test in High Dimensions using Random Projection. Arxiv paper, August 2011. Presented part at NIPS Conference, Granada, Spain, December 2011.

  • S. Negahban and M. J. Wainwright (2012). Restricted strong convexity and weighted matrix completion: Optimal bounds with noise. Journal of Machine Learning Research, 13: 1665--1697, May 2012.
    Preliminary versions.
  • Arxiv preprint, September 2010.
  • Presented at NIPS Workshops, Vancouver, Canada, December 2010.
  • S. Negahban and M. J. Wainwright (2011). Estimation of (near) low-rank matrices with noise and high-dimensional scaling. Annals of Statistics, Vol. 39, Number 2, pp. 1069--1097. Supplementary material .
    Preliminary versions:
  • Arxiv paper, December 2009: http://arxiv.org/abs/0912.5100
  • Presented in part at the International Conference on Machine Learning (ICML), Haifa, Israel. June 2010.
  • G. Raskutti, M. J. Wainwright and B. Yu (2011). Minimax rates of estimation for high-dimensional linear regression over $\ell_q$-balls. IEEE Transactions on Information Theory, 57(10):6976--6994, October 2011.
    Preliminary version:
  • Originally posted on arxiv, October 2009
  • Presented in part at the Allerton Conference on Control, Communication and Computing, September 2009, Monticello, IL.
  • P. Ravikumar, M. J. Wainwright, G. Raskutti and B. Yu (2011). High-dimensional covariance estimation by minimizing $\ell_1$-penalized log-determinant divergence. Electronic Journal of Statistics, 4:935--980, 2011.
    Preliminary versions:
  • Arxiv paper, November 2008.
  • Presented in part at the NIPS 2008 Conference, December 2008, Vancouver, Canada.
  • S. Negahban and M. J. Wainwright (2011), Simultaneous support recovery in high dimensions: Benefits and perils of block $\ell_1/\ell_\infty$-regularization. IEEE Transactions on Information Theory, 57(6):3841--3863, June 2011.
    Preliminary versions:
  • Appeared in the Advances in Neural Information Processing Systems, December 2008. Vancouver. Canada
  • UC Berkeley Technical Report 774, May 2009.
  • G. Obozinski, M. J. Wainwright, and M. I. Jordan (2011). Support union recovery in high-dimensional multivariate regression. Annals of Statistics, 39(1):1--47, January 2011.
    Preliminary versions
  • Technical report 761 Department of Statistics, UC Berkeley. August 2008.
  • Presented in part at NIPS Conference, Vancouver, Canada. December, 2008.
  • G. Raskutti, M. J. Wainwright and B. Yu (2010). Restricted nullspace and eigenvalue properties for correlated Gaussian designs. Journal of Machine Learning Research, 11:2241-2259, August 2010.

  • W. Wang, M. J. Wainwright and K. Ramchandran (2010). Information-theoretic bounds on model selection for Gaussian Markov random fields. IEEE International Symposium on Information Theory, Austin, TX.

  • W. Wang, M. J. Wainwright and K. Ramchandran (2010). Information-theoretic limits on sparse signal recovery: Dense versus sparse measurement matrices. IEEE Trans. Information Theory, June 2010. 56(6): 2967--2979.
    Preliminary versions:
  • UC Berkeley Technical Report 754, May 2008.
  • Short version presented at International Symposium on Information Theory (ISIT), Toronto, Canada. July, 2008
  • D. Omidiran and M. J. Wainwright (2010). High-dimensional variable selection with sparse random projections: Measurement sparsity and statistical efficiency. Journal of Machine Learning Research. 11:2361--2386, August 2010.
    Preliminary versions:
  • UC Berkeley Technical Report 753, May 2008.
  • Short version presented at International Symposium on Information Theory (ISIT), Toronto, Canada. July, 2008
  • P. Ravikumar, M. J. Wainwright and J. Lafferty (2010). High-dimensional Ising model selection using $\ell_1$-regularized logistic regression. Annals of Statistics, Vol. 38, Number 3. pp. 1287--1319.
    Preliminary versions:
  • Department of Statistics, Technical Report 750, April 2008.
  • M. J. Wainwright, P. Ravikumar and J. Lafferty. Advances in Neural Information Processing Systems, December 2006. Vancouver. Canada.
  • Arash A. Amini and M. J. Wainwright (2009), High-dimensional analysis of semidefinite programming relaxations for sparse principal component analysis. Annals of Statistics, Vol. 37(5B): 2877-2921, 2009.
    Preliminary versions:
  • Technical report 747, Department of Statistics, UC Berkeley. March 2008.
  • Short version presented at International Symposium on Information Theory (ISIT), Toronto, Canada. July, 2008

  • M. J. Wainwright (2009), Information-theoretic limitations on sparsity recovery in the high-dimensional and noisy setting. IEEE Transactions on Information Theory, 55:5728--5741, December 2009.
    Preliminary versions
  • Technical report 725, Department of Statistics, UC Berkeley. January 2007. Appeared on arxiv
  • Presented in part at International Symposium on Information Theory (ISIT), Nice, France, July 2007.
  • M. J. Wainwright (2009), Sharp thresholds for noisy and high-dimensional recovery of sparsity using $\ell_1$-constrained quadratic programming (Lasso). IEEE Transactions on Information Theory, 55:2183--2202, May 2009.
    Preliminary versions:
  • Technical report 709, Department of Statistics, UC Berkeley. May 2006.
  • Short version presented at Allerton Conference on Communication, Control and Computing, September 2006.

  • Graphical models and Markov random fields

  • P. Loh and M. J. Wainwright (2013). Structure estimation for discrete graphical models: Generalized covariance matrices and their inverses. Annals of Statistics, 41(6): 3022--3049. Preliminary version presented in part at NIPS 2012 Conference.

  • N. Noorshams and M. J. Wainwright (2013). Belief propagation for continuous state spaces: Stochastic message-passing with quantitative guarantees. Journal of Machine Learning Research 14, pp. 2799--2855.

  • N. Noorshams and M. J. Wainwright (2013). Stochastic Belief Propagation: A Low-Complexity Alternative to the Sum-Product Algorithm. IEEE Transactions on Information Theory, 59(4):1981--2000.

  • N. Santhanam and M. J. Wainwright (2012). Information-theoretic limits of selecting binary graphical models in high dimensions. IEEE Transactions on Information Theory, 58(7): 4117--4134, July 2012.
    Preliminary versions:
  • Presented at International Symposium on Information Theory (ISIT), Toronto, Canada. July, 2008.
  • Arxiv paper, May 2009.
  • P. Ravikumar, M. J. Wainwright, G. Raskutti and B. Yu (2011). High-dimensional covariance estimation by minimizing $\ell_1$-penalized log-determinant divergence. Electronic Journal of Statistics, 4:935--980, 2011.
    Preliminary versions:
  • Arxiv paper, November 2008.
  • Presented in part at the NIPS 2008 Conference, December 2008, Vancouver, Canada.
  • P. Ravikumar, A. Agarwal and M. J. Wainwright (2010). Message-passing for graph-structured linear programs: Proximal projections, convergence, and rounding schemes. Journal of Machine Learning Research, 11:1043--1080, March 2010.
    Preliminary conference version:
  • International Conference on Machine Learning (ICML), Helsinki, Finland. July, 2008.
  • P. Ravikumar, M. J. Wainwright and J. Lafferty (2010). High-dimensional Ising model selection using $\ell_1$-regularized logistic regression. Annals of Statistics, Vol. 38, Number 3. pp. 1287--1319.
    Preliminary version:
  • M. J. Wainwright, P. Ravikumar and J. Lafferty. Advances in Neural Information Processing Systems, December 2006. Vancouver. Canada.
  • M. J. Wainwright and M. I. Jordan (2008). Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning, Vol. 1, Numbers 1--2, pp. 1--305, December 2008.
    Preliminary versions:
  • M. J. Wainwright, and M. I. Jordan. Variational inference in graphical models: The view from the marginal polytope. Invited paper; Allerton Conference on Communication, Control, and Computing; October 1--3, 2003; Urbana-Champaign, IL
  • M. J. Wainwright, and M. I. Jordan. Graphical models, exponential families, and variational inference. UC Berkeley, Dept. of Statistics, Technical Report 649. September, 2003.
  • T. G. Roosta, M. J. Wainwright and S. S. Sastry (2008). Convergence analysis of reweighted sum-product algorithms. IEEE Trans. Signal Processing 56(9): 4293--4305, September 2008.

  • E. B. Sudderth, M. J. Wainwright, and A. S. Willsky Loop series and Bethe variational bounds in attractive graphical models. Proceedings of the NIPS conference, Vancouver, Canada. December 2007.

  • M. J. Wainwright (2006). Estimating the ``wrong'' graphical model: Benefits in the computation-limited setting. Journal of Machine Learning Research, 7:1829--1859. September 2006.
    Preliminary versions:
  • M. J. Wainwright. NIPS Conference, December 2005, Vancouver, Canada.
  • M. J. Wainwright and M. I. Jordan, Log-determinant relaxation for approximate inference in discrete Markov random fields. IEEE Transactions on Signal Processing, Vol. 54(6), pages 2099--2109. June 2006.
    Preliminary versions:
  • Appeared previously as UC Berkeley, Department of EECS, Technical Report UCB/CSD-3-1226, January 2003 (outdated).
  • M. J. Wainwright and M. I. Jordan. NIPS Conference, December 2003, Vancouver, Canada.
  • E. Maneva, E. Mossel and M. J. Wainwright. A New Look at Survey Propagation and its Generalizations. Journal of the ACM, Volume 54(4), July 2007. pp. 2--41.
    Preliminary version: Extended abstract at Symposium on Discrete Algorithms (SODA), January 2005, Vancouver, Canada.

  • V. N. Kolmogorov and M. J. Wainwright. On optimality of tree-reweighted max-product message-passing. Appeared in Uncertainty in Artificial Intelligence, July 2005, Edinburgh, Scotland.

  • M. J. Wainwright, T. S. Jaakkola and A. S. Willsky (2005). MAP estimation via agreement on (hyper)trees: Message-passing and linear-programming approaches. IEEE Transactions on Information Theory, Vol. 51(11), pages 3697--3717. November 2005.
    Preliminary versions:
  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. Exact MAP estimates by (hyper)tree agreement. NIPS conference; December, 2002; Vancouver, BC, Canada.
  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. MAP estimation via agreement on (hyper)trees: Message-passing and linear programming approaches. Allerton Conference on Communication, Control, and Computing; October 2--4, 2002; Urbana-Champaign, IL
  • M. J. Wainwright and M. I. Jordan. Treewidth-based conditions for exactness of the Sherali-Adams and Lasserre relaxations. UC Berkeley, Dept. of Statistics, Technical Report 671. September, 2004.

  • M. J. Wainwright, T. Jaakkola and A. S. Willsky (2005). A new class of upper bounds on the log partition function. IEEE Trans. on Information Theory, vol. 51, page 2313--2335, July 2005.
    Preliminary versions:
  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. Uncertainty in Artificial Intelligence; August 1--4, 2002; Edmonton, CA. Best Paper Award
  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. (2003) Tree-reweighted belief propagation and approximate ML estimation by pseudo-moment matching. Presented at the 9th Workshop on Artificial Intelligence and Statistics, Key West, Florida; January, 2003

  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. (2004) Tree consistency and bounds on the performance of the max-product algorithm and its generalizations. Statistics and Computing, April 2004, Vol. 14, 143--166.
    Journal version:

  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. Tree-based reparameterization framework for analysis of sum-product and related algorithms. IEEE Transactions on Information Theory, 45(9): pages 1120--1146.
    Preliminary version:
  • M. J. Wainwright, T. Jaakkola and A. S. Willsky. NIPS Conference 2002, Runner-up Best Student Paper Award
  • E. Sudderth, M. J. Wainwright and A. S. Willsky. Embedded trees: Estimation of Gaussian processes on graphs with cycles. IEEE Transactions on Signal Processing, November 2004, Vol. 52, pp. 3136 --3150.
    Preliminary version:
  • M. J. Wainwright, E. Sudderth and A. S. Willsky. Presented at the Conference on Neural Information Processing Systems (NIPS). Denver, CO. Nov. 28--30, 2000.
  • Back to top


    Nonparametric statistics

  • Y. Yang, M. Pilanci, M. J. Wainwright (2017). Randomized sketches for kernels: Fast and optimal nonparametric regression. Annals of Statistics. 45(3):991--1023.

  • A. El Alaoui, X. Cheng, A. Ramdas, M. J. Wainwright and M. I. Jordan (2016). Asymptotic behavior of $\ell_p$-based Laplacian regularization in semi-supervised learning. Presented in part at the COLT conference, June 2016.

  • G. Schiebinger, M. J. Wainwright and B. Yu (2015). The geometry of kernelized spectral clustering. . Annals of Statistics, 43(2):819--846, March 2015.

  • G. Raskutti, M. J. Wainwright and B. Yu (2014). Early stopping and non-parametric regression: An optimal data-dependent stopping rule. Journal of Machine Learning Research, 15:335--366. Conference version presented at Allerton Conference, October 2011.

  • Y. Zhang, J. C. Duchi and M. J. Wainwright (2015). Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates. Journal of Machine Learning Research, 16: 3299--3340, December 2015. Preliminary version presented at at the COLT Conference, 2013.

  • A. Amini and M. J. Wainwright (2012). Sampled forms of functional PCA in reproducing kernel Hilbert spaces. Annals of Statistics, 40(5):2483--2510.

  • G. Raskutti, M. J. Wainwright and B. Yu (2012). Minimax-optimal rates for sparse additive models over kernel classes via convex programming. Journal of Machine Learning Research, 13:389--427. March 2012.
    Short version appeared at the NIPS Conference, Vancouver, Canada. December 2009.

  • A. Amini and M. J. Wainwright (2011). Approximation properties of certain operator-induced norms on Hilbert spaces. Journal of Approximation Theory, Vol 164: 320--345.

  • X. Nguyen, M. J. Wainwright and M. I. Jordan (2010). Estimating divergence functionals and the likelihood ratio by convex risk minimization. IEEE Transactions on Information Theory, 56:(11), pages 5847--5861, November 2010.
    Preliminary version:
  • Presented in part at the International Symposium on Information Theory, Nice, France. July 2007.
  • Arxiv technical report, 2008
  • X. Nguyen, M. J. Wainwright and M. I. Jordan (2009). On divergences, surrogate loss functions, and f-divergences. Annals of Statistics, 37(2): 876--904.
    Preliminary version:
  • UC Berkeley Department of Statistics, Technical Report 695, October 2005.
  • X. Nguyen, M. J. Wainwright and M. I. Jordan. 43rd Annual Allerton Conference on Communication, Control and Computing, IL, September 2005.
  • X. Nguyen, M. J. Wainwright and M. I Jordan. Nonparametric decentralized detection using kernel methods. IEEE Transactions on Signal Processing, Vol. 53(11), pages 4053--4066. November 2005. IEEE Signal Processing Outstanding Young Author Award (XuanLong Nguyen)

    Optimization in statistical settings

  • Y. Yang, M. Pilanci, M. J. Wainwright (2017). Randomized sketches for kernels: Fast and optimal nonparametric regression. Annals of Statistics. 45(3):991--1023.

  • M. Pilanci and M. J. Wainwright (2017). Newton Sketch: A Linear-time optimization algorithm with linear-quadratic convergence. SIAM Journal of Optimization. 27(1): 205--245.

  • F. Yang, S. Balakrishnan, and M. J. Wainwright (2017). Statistical and Computational Guarantees for the Baum-Welch Algorithm. Journal of Machine Learning Research, 18(125): 1--53. Initially posted as arxiv pre-print, December 2015

  • M. Pilanci and M. J. Wainwright (2016). Iterative Hessian Sketch: Fast and accurate solution approximation for constrained least-squares. Journal of Machine Learning Research 17:1--38.

  • C. Jin, Y. Zhang, S. Balakrishnan, M. J. Wainwright and M. I. Jordan (2016). Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences. Arxiv pre-print, September 2016. Short version appeared at NIPS Conference, December 2016.

  • M. Pilanci and M. J. Wainwright (2015) Randomized Sketches of Convex Programs with Sharp Guarantees. IEEE Transactions on Information Theory, 61(9): 5096--5115, September 2015.

  • Y. Chen and M. J. Wainwright (2015). Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees Arxiv pre-print, September 2015.

  • Y. Zhang, M. J. Wainwright, and M. I. Jordan (2015). Distributed estimation of generalized matrix rank: Efficient algorithms and lower bounds. Proceedings of The 32nd International Conference on Machine Learning, pp. 457--465, 2015.

  • S. Balakrishnan, M. J. Wainwright and B. Yu (2014). Statistical guarantees for the EM algorithm: From population to sample-based analysis. Arxiv pre-print, August 2014.

  • J. C. Duchi, M. I. Jordan, M. J. Wainwright and Y. Zhang (2014). Optimality guarantees for distributed statistical estimation. Arxiv pre-print, May 2014. Short version appeared at NIPS 2013.

  • J. C. Duchi, M. I. Jordan, M. J. Wainwright and A. Wibisono (2015). Optimal rates for zero-order convex optimization: the power of two function evaluations. IEEE. Transactions on Inofrmation Theory, 61(5): 2788--2806, May 2015.

  • Y. Zhang, J. C. Duchi and M. J. Wainwright (2015). Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates. Journal of Machine Learning Research, 16: 3299--3340, December 2015. Preliminary version presented at at the COLT Conference, 2013.

  • Y. Zhang, J. C. Duchi and M. J. Wainwright (2013). Communication-efficient algorithms for statistical optimization. Journal of Machine Learning Research. 14:3321--3363, November 2013. Short version presented at NIPS Conference, December 2012.

  • A. Agarwal, S. Negahban, and M. J. Wainwright (2012). Stochastic optimization and sparse statistical recovery: An optimal algorithm for high dimensions. Arxiv pre-print, July 2012. Short version presented at NIPS Conference, December 2012.

  • J. C. Duchi, P. L. Bartlett, and M. J. Wainwright (2012). Randomized smoothing for stochastic optimization. SIAM Journal on Optimization, 22(2):674--701.
  • Preliminary version: Arxiv technical report, March 2011.
  • A. Agarwal, S. Negahban, and M. J. Wainwright (2012). Fast global convergence of gradient methods for high-dimensional statistical recovery. Annals of Statistics, 40(5):2452---2482.
  • Supplementary material (30 pages)
  • Preliminary versions:
  • Short version appeared at NIPS Conference, Vancouver, Canada. December 2010.
  • Arxiv paper posted April 2011.
  • J. Duchi, A. Agarwal, and M. J. Wainwright (2012). Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling, IEEE Transactions on Automatic Control, 57(3):592--606, March 2012.
    Short version:
  • Appeared in Proceedings of NIPS Conference, December 2010, Vancouver. Canada.
  • A. Agarwal, P. Bartlett, P. Ravikumar and M. J. Wainwright (2012). Information-theoretic lower bounds on the oracle complexity of convex optimization. IEEE Transactions on Information Theory, 58(5):3235--3249, May 2012.
    Preliminary versions:
  • Arxiv pre-print posted September 2010
  • Appeared in Proceedings of NIPS Conference, December 2009, Vancouver. Canada.
  • N. Noorshams and M. J. Wainwright (2011). Non-asymptotic analysis of an optimal algorithm for network-constrained averaging with noisy links. IEEE Journal on Selected Topics in Signal Processing, 5(4):833--844, August 2011.
    Preliminary versions:
  • Conference paper, Presented in part at International Symposium on Information Theory, Austin, Texas. July 2011.
  • R. Rajagopal and M. J. Wainwright (2011). Network-based consensus averaging with general noisy channels. IEEE Transactions on Signal Processing, 59(1):373--385, January 2011
    Preliminary versions:
  • Presented in part at Allerton Conference on Control, Communication, and Computing (Sep. 2007).
  • UC Berkeley Technical Report 751, May 2008.

  • X. Nguyen, M. J. Wainwright and M. I. Jordan (2008). On optimal quantization rules for some problems in sequential decentralized detection. IEEE Transactions on Information Theory, Vol. 54(7), pp. 3285--3295. July 2008.
    Preliminary versions:
  • Presented in part at International Symposium on Information Theory, Seattle, WA. July 2006.
  • Longer version appeared originally as Technical Report 708, Department of Statistics, UC Berkeley. August 2006.
  • A. G. Dimakis, A. Sarwate and M. J. Wainwright (2008). Geographic Gossip: Efficient Averaging for Sensor Networks. IEEE Transactions on Signal Processing, 53: 1205--1216. March 2008.
    Conference version:
  • Fifth International Conference on Information Processing in Sensor Networks (IPSN), Nashville, TN. April 2006.
  • M. Cetin, L. Chen, J. Fisher, A. Ihler, R. Moses, M. J. Wainwright and A. S. Willsky (2006). Distributed fusion in sensor networks. IEEE Signal Processing Magazine, July 2006.

  • R. Rajagopal, M. J. Wainwright and P. Varaiya, Universal Quantile Estimation with Feedback in the Communication-Constrained Setting, International Symposium on Information Theory, Seattle, WA. July 2006.

  • X. Nguyen, M. J. Wainwright and M. I Jordan. Nonparametric decentralized detection using kernel methods. IEEE Transactions on Signal Processing, Vol. 53(11), pages 4053--4066. November 2005. IEEE Signal Processing Outstanding Young Author Award (XuanLong Nguyen)
    Preliminary versions:
  • X. Nguyen, M. J. Wainwright and M. I Jordan. Decentralized detection and classification using kernel methods. Proceedings of the International Conference on Machine Learning, July 2004. Outstanding Student Paper Award (XuanLong Nguyen)

  • L. Chen, M. J. Wainwright, M. Cetin and A. Willsky, Multitarget-multisensor data association using the tree-reweighted max-product algorithm. Presented at the SPIE Aerosense conference, Orlando, FL, March 2003.

    Back to top


    Permutations, rankings, and related problems

  • A. Pananjady, M. J. Wainwright and T. Courtade (2018). Linear Regression with an Unknown Permutation: Statistical and Computational Limits To appear in the IEEE Transactions on Information Theory. Arxiv pre-print, August 2016. Presented in part at the Allerton Conference on Control, Computing and Communication (2016).

  • N. B. Shah and M. J. Wainwright (2018), Simple, Robust and Optimal Ranking from Pairwise Comparisons To appear in Journal of Machine Learning Research. First posted as Arxiv pre-print, December 2015.

  • R. Heckel, M. Simchowitz, K. Ramchandran and M. J. Wainwright (2018). Approximate Ranking from Pairwise Comparisons Arxiv pre-print. January 2018. To be presented in part at AISTATS 2018.

  • A. Pananjady, M. J. Wainwright and T. Courtade (2017) Denoising linear models with permuted data. Arxiv pre-print, April 2017. Presented in part at ISIT 2017, Aachen, Germany. July 2017.

  • N. B. Shah, S. Balakrishan, M. J. Wainwright and A. Guntuboyina (2017) Stochastically transitive models for pairwise comparisons: Statistical and computational issues. IEEE Trans. Info. Theory, 63(2): 934--959, February 2017.

  • R. Heckel, N. B. Shah, K. Ramchandran and M. J. Wainwright (2016), Active Ranking from Pairwise Comparisons and when Parametric Assumptions Don't Help. Arxiv pre-print, June 2016.

  • N. B. Shah, S. Balakrishnan and M. J. Wainwright (2016), A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness Arxiv pre-print, June 2016.

  • H. Mania, A. Ramdas, M. J. Wainwright, M. I. Jordan, and B. Recht (2016). Universality of Mallows' and degeneracy of Kendall's kernels for rankings. Arxiv pre-print, March 2016.

  • N. B. Shah, S. Balakrishan and M. J. Wainwright (2016) Feeling the Bern: Adaptive Estimators for Bernoulli Probabilities of Pairwise Comparisons, Arxiv pre-print, March 2016.

  • N. B. Shah, S. Balakrishnan, J. Bradley, A. Parekh, K. Ramchandran, and M. J. Wainwright (2015), Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence , Arxiv pre-print, To appear in Journal of Machine Learning Research.

  • N. B. Shah, J. Bradley, A. Parekh, M. J. Wainwright, and K. Ramchandran (2013). A Case for Ordinal Peer-evaluation in MOOCs. Neural Information Processing Systems (NIPS): Workshop on Data Driven Education, Lake Tahoe, Dec. 2013.

    Channel coding, data compression, algorithms

  • N. Noorshams and M. J. Wainwright (2010), Lossy source coding with sparse graph codes: A variational formulation of soft decimation. Proceedings of the Allerton Conference on Control, Communication and Computing, Monticello, IL, September 2010.

  • A. Dimakis, B. Godfrey, M. J. Wainwright and K. Ramchandran (2010), Network Coding for Distributed Storage Systems, IEEE Transactions on Information Theory. 56(9):4539--4551, September 2010. IEEE Communications Society, Best Paper Award (2010)

    Preliminary version: Appeared in Proceedings of INFOCOM 2007, Anchorage, Alaska. May 2007.

  • Z. Zhang, V. Anantharam, M. J. Wainwright and B. Nikolic, (2010) An efficient 10GBASE-T Ethernet LDPC decoder design with low error floors , IEEE Jour. Solid-State Circuits, 45(4):843--855, March 2010.

  • M. J. Wainwright, E. Maneva, and E. Martinian (2010). Lossy Source Compression Using Low-Density Generator Matrix Codes: Analysis and Algorithms, IEEE Transactions on Information Theory. 56(3):1351--1368. March 2010.
    Preliminary versions:
  • E. Martinian and M. J. Wainwright, Analysis of LDGM and compound codes for lossy compression and binning. Workshop on Information Theory and its Applications, San Diego, CA. February 2006.
  • M. J. Wainwright and E. Maneva, Lossy source coding via message-passing and decimation over generalized codewords of LDGM codes. Presented at the International Symposium on Information Theory, Adelaide, Australia. September, 2005.
  • L. Dolecek, Z. Zhang, V. Anatharam, M. J. Wainwright and B. Nikolic (2010). Analysis of Absorbing Sets and Fully Absorbing Sets of Array-Based LDPC Codes. IEEE Transactions on Information Theory, 56(1):181--201, January 2010.

  • Z. Zhang, L. Dolecek, B. Nikolic, V. Anantharam, and M. J. Wainwright (2009). Design of LDPC decoders for improved low error rate performance: Quantization and algorithm choices. IEEE Transactions on Wireless Communications, 8(11):3258--3268, November 2009.

    Preliminary versions:

  • Z. Zhang, L. Dolecek, V. Anantharam, M. J. Wainwright, and B. Nikolic, Quantization Effects in Low-Density Parity-Check Decoders, IEEE International Conference on Communications (ICC), Glasgow, United Kingdom, June 2007, pp. 6231-6237.
  • Z. Zhang, L. Dolecek, B. Nikolic, V. Anantharam, and M. J. Wainwright. Investigation of error floors of structured low-density parity-check codes by hardware emulation. Proceedings of IEEE Globecom, San Francisco, CA, November 2006.
  • A. G.. Dimakis, A. A. Gohari and M. J. Wainwright (2009). Guessing Facets: Polytope Structure and Improved LP Decoding. IEEE Transactions on Information Theory. 55(8):3479--3478, August 2009.
    Preliminary version:
  • International Symposium on Information Theory, Seattle, WA. July 2006.
  • L. Dolecek, P. Lee, Z. Zhang, V. Anatharam, B. Nikolic and M. J. Wainwright (2009) Predicting error floors of structured LDPC codes: Deterministic bounds and estimates. IEEE Journal on Selected Areas in Communications, 27(6):908--917, August 2009.
    Preliminary version:
  • P. Lee, L. Dolecek, Z. Zhang, V. Anantharam, B. Nikolic and M. J . Wainwright, Error Floors in LDPC Codes: Fast Simulation, Bounds and Hardware Emulation. IEEE International Symposium on Information Theory (ISIT 2008), Toronto, Canada, July 2008. Full Text  (PDF)
  • M. J. Wainwright and E. Martinian (2009), Low-density graph codes that are optimal for source/channel coding and binning. IEEE Trans. Information Theory, 55(3):1061--1079. March 2009.
    Preliminary versions:
  • Department of Statistics, Technical Report 730, April 2007.
  • M. J. Wainwright and E. Martinian, Low-density constructions can achieve the Wyner-Ziv and Gelfand-Pinsker bounds. International Symposium on Information Theory, Seattle, WA. July 2006. Full Text  (151K  pdf)
  • E. Martinian and M. J. Wainwright, Low-density codes achieve the rate-distortion bound. Data Compression Conference, Snowbird, UT. March 2006. Full Text (191K  pdf)
  • C. Daskalakis, A. G. Dimakis, R. Karp and M. J. Wainwright (2008). Probabilistic analysis of linear programming decoding. IEEE. Trans. Information Theory, Vol. 54(8): pp. 3565--3578, August 2008.

    Preliminary version: Extended abstract in SIAM Symposium on Discrete Algorithms, New Orleans, LA. January 2007.

  • A. D. G. Dimakis, M. J. Wainwright, M.J., and K. Ramchandran, Lower bounds on the rate-distortion function of LDGM codes. Information Theory Workshop (ITW), September 2007, pp. 650 - 655.

  • M. J. Wainwright, Sparse graph codes for side information and binning, IEEE Signal Processing Magazine: 24(5): 47--57, September 2007.

  • L. Dolecek, Z. Zhang, M. J. Wainwright, V. Anantharam, and B. Nikolic, Evaluation of the low frame error rate performance of LDPC codes using importance sampling, IEEE Information Theory Workshop, Lake Tahoe CA, September 2007, pp. 202 - 207.

  • L. Dolecek, Z. Zhang, V. Anantharam, M. J. Wainwright, and B. Nikolic (2010), Analysis of Absorbing Sets and Fully Absorbing Sets of Array-Based LDPC Codes. IEEE Trans. Info. Theory 56(1): 181--201, March 2010.

    • Preliminary version: Analysis of Absorbing Sets for Array-Based LDPC Codes, IEEE International Conference on Communications (ICC), Glasgow, United Kingdom, June 2007, pp. 6261-6268.

  • J. Feldman, T. Malkin, R. Servedio, C. Stein and M. J. Wainwright, LP Decoding Corrects a Constant Fraction of Errors. IEEE Trans. Information Theory, (53):82--89. January, 2007.
    Preliminary versions:
  • Presented at International Symposium on Information Theory, Chicago, IL. July, 2004.
  • J. Feldman, M. J. Wainwright and D. R. Karger. (2005) Using linear programming to decode binary linear codes. IEEE Transactions on Information Theory, (51):954-972.
    Preliminary versions:
  • J. Feldman, D. Karger and M. Wainwright, Using linear programming to decode LDPC codes. Conference on Information Sciences and Systems, Baltimore, March 2003.
  • J. Feldman, D. Karger and M. Wainwright, Linear programming-based decoding of turbo-like codes and its relation to iterative approaches. Presented at the Allerton Conference on Communication, Control, and Computing; October 2--4, 2002; Urbana-Champaign, IL.
  • Back to list


    Natural image models and statistical image processing

  • J. Portilla, V. Strela, M. J. Wainwright and E.P. Simoncelli. Image denoising using Gaussian scale mixtures in the wavelet domain. IEEE Transactions on Image Processing, November 2003. Vol. 12, pp. 1338-1351. IEEE Signal Processing Society, Best Paper Award (2008)

    Preliminary version:

  • J. Portilla, V. Strela, M. J. Wainwright and E.P. Simoncelli. Adaptive Wiener denoising using a Gaussian scale mixture model in the wavelet domain. Proceedings of the 8th International Conference on Image Processing. October, 2001; Greece.
  • M. J. Wainwright, E. P. Simoncelli and A. S. Willsky. Random cascades on wavelet trees and their use in analyzing and modeling natural images. Applied Computational and Harmonic Analysis (2001), vol. 11, pages 89--123.

    Preliminary versions:
  • M. J. Wainwright, E. P. Simoncelli and A. S. Willsky. Random cascades on wavelet trees and their use in analyzing and modeling natural images. Invited Paper; Published in Proceedings of the 45th Annual Meeting of the SPIE. San Diego, CA; July 30 -- August 4, 2000.
  • M. J. Wainwright, E. P. Simoncelli and A. S. Willsky. Random cascades of Gaussian scale mixtures and their use in modeling natural images with application to denoising. Proceedings of the 7th International Conference on Image Processing. Vancouver, BC, Canada. 10-13 September 2000.

  • M. J. Wainwright and E. P. Simoncelli. Scale Mixtures of Gaussians and the Statistics of Natural Images. Conference on Neural Information Processing Systems (NIPS). Denver, CO. Nov 29-Dec 2, 1999; pages 855--861.
  • Back to top


    Statistical theories of biological vision

  • M. J. Wainwright, O. Schwartz, and E. P. Simoncelli, Natural image statistics and divisive normalization: Modeling nonlinearities and adaptation in cortical neurons, Chapter 10, pages 203--222; Statistical Theories of the Brain, Eds. P. Rao, B. Olshausen and M. Lewicki, MIT Press 2002.

  • M. J. Wainwright, Visual adaptation as optimal information transmission. Vision Research , 39:3960--3974, 1999.

    Back to top


    Ph.D. thesis

  • M. J. Wainwright, "Stochastic Processes on Graphs: Geometric and Variational Approaches", Ph.D. Thesis, Department of EECS, Massachusetts Institute of Technology, 2002. Full Text (3.9M, pdf)