2024
A Diffusion Process Perspective on Posterior Contraction Rates for Parameters.
SIAM J. Math. Data Sci., 2024
Sharp Results for Hypothesis Testing with Risk-Sensitive Agents.
CoRR, 2024
Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning.
CoRR, 2024
Finite-Sample Guarantees for Best-Response Learning Dynamics in Zero-Sum Matrix Games.
CoRR, 2024
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
2023
Optimal Oracle Inequalities for Projected Fixed-Point Equations, with Applications to Policy Evaluation.
Math. Oper. Res., 2023
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning.
J. Mach. Learn. Res., 2023
Revisiting minimum description length complexity in overparameterized models.
J. Mach. Learn. Res., 2023
Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing.
CoRR, 2023
Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints.
CoRR, 2023
Semi-parametric inference based on adaptively collected data.
CoRR, 2023
A finite-sample analysis of multi-step temporal difference estimates.
Proceedings of the Learning for Dynamics and Control Conference, 2023
Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023
2022
Minimax Off-Policy Evaluation for Multi-Armed Bandits.
IEEE Trans. Inf. Theory, 2022
An Efficient Sampling Algorithm for Non-smooth Composite Potentials.
J. Mach. Learn. Res., 2022
Policy evaluation from a single path: Multi-step methods, mixing and mis-specification.
CoRR, 2022
Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency.
CoRR, 2022
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning.
CoRR, 2022
Optimally tackling covariate shift in RKHS-based nonparametric regression.
CoRR, 2022
Optimal variance-reduced stochastic approximation in Banach spaces.
CoRR, 2022
Bellman Residual Orthogonalization for Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022
Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning.
Proceedings of the International Conference on Machine Learning, 2022
A new similarity measure for covariate shift with applications to nonparametric regression.
Proceedings of the International Conference on Machine Learning, 2022
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022
ROOT-SGD: Sharp Nonasymptotics and Asymptotic Efficiency in a Single Algorithm.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022
2021
A Permutation-Based Model for Crowd Labeling: Optimal Estimation and Robustness.
IEEE Trans. Inf. Theory, 2021
Instance-Dependent ℓ<sub>∞</sub>-Bounds for Policy Evaluation in Tabular Reinforcement Learning.
IEEE Trans. Inf. Theory, 2021
Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis.
SIAM J. Math. Data Sci., 2021
High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm.
J. Mach. Learn. Res., 2021
Optimal policy evaluation using kernel-based temporal difference methods.
CoRR, 2021
Near-optimal inference in adaptive linear regression.
CoRR, 2021
Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning.
CoRR, 2021
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
2020
The Local Geometry of Testing in Ellipses: Tight Control via Localized Kolmogorov Widths.
IEEE Trans. Inf. Theory, 2020
Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems.
J. Mach. Learn. Res., 2020
Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients.
J. Mach. Learn. Res., 2020
Optimal oracle inequalities for solving projected fixed-point equations.
CoRR, 2020
Revisiting complexity and the bias-variance tradeoff.
CoRR, 2020
Instability, Computational Efficiency and Statistical Accuracy.
CoRR, 2020
Lower bounds in multiple testing: A framework based on derandomized proxies.
CoRR, 2020
HopSkipJumpAttack: A Query-Efficient Decision-Based Attack.
Proceedings of the 2020 IEEE Symposium on Security and Privacy, 2020
FedSplit: an algorithmic framework for fast federated optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Preference learning along multiple criteria: A game-theoretic perspective.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration.
Proceedings of the Conference on Learning Theory, 2020
Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020
2019
Early Stopping for Kernel Boosting Algorithms: A General Analysis With Localized Complexities.
IEEE Trans. Inf. Theory, 2019
Feeling the Bern: Adaptive Estimators for Bernoulli Probabilities of Pairwise Comparisons.
IEEE Trans. Inf. Theory, 2019
Low Permutation-rank Matrices: Structural Properties and Noisy Completion.
J. Mach. Learn. Res., 2019
Convergence Guarantees for a Class of Non-convex and Non-smooth Optimization Problems.
J. Mach. Learn. Res., 2019
Log-concave sampling: Metropolis-Hastings algorithms are fast.
J. Mach. Learn. Res., 2019
Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing.
CoRR, 2019
Value function estimation in Markov reward processes: Instance-dependent 𝓁<sub>∞</sub>-bounds for policy evaluation.
CoRR, 2019
Variance-reduced Q-learning is minimax optimal.
CoRR, 2019
Stochastic approximation with cone-contractive operators: Sharp 𝓁<sub>∞</sub>-bounds for Q-learning.
CoRR, 2019
Challenges with EM in application to weakly identifiable mixture models.
CoRR, 2019
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data.
Proceedings of the 7th International Conference on Learning Representations, 2019
2018
Linear Regression With Shuffled Data: Statistical and Computational Limits of Permutation Recovery.
IEEE Trans. Inf. Theory, 2018
Fast MCMC Sampling Algorithms on Polytopes.
J. Mach. Learn. Res., 2018
Towards Optimal Estimation of Bivariate Isotonic Matrices with Unknown Permutations.
CoRR, 2018
From Gauss to Kolmogorov: Localized Measures of Complexity for Ellipses.
CoRR, 2018
Breaking the 1/√n Barrier: Faster Rates for Permutation-based Models in Polynomial Time.
CoRR, 2018
Theoretical guarantees for EM under misspecified Gaussian mixture models.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate.
Proceedings of the 35th International Conference on Machine Learning, 2018
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation.
Proceedings of the 35th International Conference on Machine Learning, 2018
Breaking the $1/\sqrtn$ Barrier: Faster Rates for Permutation-based Models in Polynomial Time.
Proceedings of the Conference On Learning Theory, 2018
Approximate ranking from pairwise comparisons.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018
2017
Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues.
IEEE Trans. Inf. Theory, 2017
Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence.
SIAM J. Optim., 2017
Statistical and Computational Guarantees for the Baum-Welch Algorithm.
J. Mach. Learn. Res., 2017
Simple, Robust and Optimal Ranking from Pairwise Comparisons.
J. Mach. Learn. Res., 2017
The local geometry of testing in ellipses: Tight control via localized Kolomogorov widths.
CoRR, 2017
DAGGER: A sequential algorithm for FDR control on DAGs.
CoRR, 2017
The geometry of hypothesis testing over convex cones: Generalized likelihood tests and minimax radii.
CoRR, 2017
Worst-case vs Average-case Design for Estimation from Fixed Pairwise Comparisons.
CoRR, 2017
A framework for Multi-A(rmed)/B(andit) Testing with Online FDR Control.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Online control of the false discovery rate with decaying memory.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Kernel Feature Selection via Conditional Covariance Minimization.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Denoising linear models with permuted data.
Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017
Convexified Convolutional Neural Networks.
Proceedings of the 34th International Conference on Machine Learning, 2017
QuTE: Decentralized multiple testing on sensor networks with false discovery rate control.
Proceedings of the 56th IEEE Annual Conference on Decision and Control, 2017
Vaidya walk: A sampling algorithm based on the volumetric barrier.
Proceedings of the 55th Annual Allerton Conference on Communication, 2017
On the Learnability of Fully-Connected Neural Networks.
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017
2016
Estimation from Pairwise Comparisons: Sharp Minimax Bounds with Topology Dependence.
J. Mach. Learn. Res., 2016
Iterative Hessian Sketch: Fast and Accurate Solution Approximation for Constrained Least-Squares.
J. Mach. Learn. Res., 2016
A Practical Scheme and Fast Algorithm to Tune the Lasso With Optimality Guarantees.
J. Mach. Learn. Res., 2016
Function-Specific Mixing Times and Concentration Away from Equilibrium.
CoRR, 2016
Universality of Mallows' and degeneracy of Kendall's kernels for rankings.
CoRR, 2016
Active Ranking from Pairwise Comparisons and the Futility of Parametric Assumptions.
CoRR, 2016
Minimax Optimal Procedures for Locally Private Estimation.
CoRR, 2016
Asymptotic behavior of ℓ<sub>p</sub>-based Laplacian regularization in semi-supervised learning.
CoRR, 2016
Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016
Sharp minimax bounds for testing discrete monotone distributions.
Proceedings of the IEEE International Symposium on Information Theory, 2016
Linear regression with an unknown permutation: Statistical and computational limits.
Proceedings of the 54th Annual Allerton Conference on Communication, 2016
2015
Randomized Sketches of Convex Programs With Sharp Guarantees.
IEEE Trans. Inf. Theory, 2015
Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations.
IEEE Trans. Inf. Theory, 2015
Sparse learning via Boolean relaxations.
Math. Program., 2015
Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates.
J. Mach. Learn. Res., 2015
Regularized M-estimators with nonconvexity: statistical and algorithmic theory for local optima.
J. Mach. Learn. Res., 2015
Learning Halfspaces and Neural Networks with Random Initialization.
CoRR, 2015
On the Computational Complexity of High-Dimensional Bayesian Variable Selection.
CoRR, 2015
Randomized sketches for kernels: Fast and optimal non-parametric regression.
CoRR, 2015
Newton Sketch: A Linear-time Optimization Algorithm with Linear-Quadratic Convergence.
CoRR, 2015
Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees.
CoRR, 2015
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds.
Proceedings of the 32nd International Conference on Machine Learning, 2015
2014
Early stopping and non-parametric regression: an optimal data-dependent stopping rule.
J. Mach. Learn. Res., 2014
When is it Better to Compare than to Score?
CoRR, 2014
Support recovery without incoherence: A case for nonconvex regularization.
CoRR, 2014
Statistical guarantees for the EM algorithm: From population to sample-based analysis.
CoRR, 2014
Lower bounds on the performance of polynomial-time algorithms for sparse linear regression.
Proceedings of The 27th Conference on Learning Theory, 2014
Stochastic optimization and sparse statistical recovery: An optimal algorithm for high dimensions.
Proceedings of the 48th Annual Conference on Information Sciences and Systems, 2014
2013
Stochastic Belief Propagation: A Low-Complexity Alternative to the Sum-Product Algorithm.
IEEE Trans. Inf. Theory, 2013
Communication-efficient algorithms for statistical optimization.
J. Mach. Learn. Res., 2013
Belief propagation for continuous state spaces: stochastic message-passing with quantitative guarantees.
J. Mach. Learn. Res., 2013
Distance-based and continuum Fano inequalities with applications to statistical estimation.
CoRR, 2013
Optimal rates for zero-order optimization: the power of two function evaluations.
CoRR, 2013
Information-theoretic lower bounds for distributed statistical estimation with communication constraints.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013
Local Privacy and Minimax Bounds: Sharp Rates for Probability Estimation.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013
Local Privacy and Statistical Minimax Rates.
Proceedings of the 54th Annual IEEE Symposium on Foundations of Computer Science, 2013
Divide and Conquer Kernel Ridge Regression.
Proceedings of the COLT 2013, 2013
2012
Information-Theoretic Limits of Selecting Binary Graphical Models in High Dimensions.
IEEE Trans. Inf. Theory, 2012
Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization.
IEEE Trans. Inf. Theory, 2012
Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling.
IEEE Trans. Autom. Control., 2012
Randomized Smoothing for Stochastic Optimization.
SIAM J. Optim., 2012
Minimax-Optimal Rates For Sparse Additive Models Over Kernel Classes Via Convex Programming.
J. Mach. Learn. Res., 2012
Restricted Strong Convexity and Weighted Matrix Completion: Optimal Bounds with Noise.
J. Mach. Learn. Res., 2012
Approximation properties of certain operator-induced norms on Hilbert spaces.
J. Approx. Theory, 2012
Discussion: Latent variable graphical model selection via convex optimization
CoRR, 2012
Comunication-Efficient Algorithms for Statistical Optimization
CoRR, 2012
FASt global convergence of gradient methods for solving regularized M-estimation.
Proceedings of the IEEE Statistical Signal Processing Workshop, 2012
Structure estimation for discrete graphical models: Generalized covariance matrices and their inverses.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012
Finite Sample Convergence Rates of Zero-Order Stochastic Optimization Methods.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012
Stochastic optimization and sparse statistical recovery: Optimal algorithms for high dimensions.
Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012
Quantized stochastic belief propagation: Efficient message-passing for continuous state spaces.
Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012
Corrupted and missing predictors: Minimax bounds for high-dimensional linear regression.
Proceedings of the 2012 IEEE International Symposium on Information Theory, 2012
Randomized smoothing for (parallel) stochastic optimization.
Proceedings of the 51th IEEE Conference on Decision and Control, 2012
Dual averaging for distributed optimization.
Proceedings of the 50th Annual Allerton Conference on Communication, 2012
2011
Network-Based Consensus Averaging With General Noisy Channels.
IEEE Trans. Signal Process., 2011
Minimax Rates of Estimation for High-Dimensional Linear Regression Over <sub>q</sub> -Balls.
IEEE Trans. Inf. Theory, 2011
Simultaneous Support Recovery in High Dimensions: Benefits and Perils of Block <sub>1</sub>/ <sub>INFINITY </sub> -Regularization.
IEEE Trans. Inf. Theory, 2011
Non-Asymptotic Analysis of an Optimal Algorithm for Network-Constrained Averaging With Noisy Links.
IEEE J. Sel. Top. Signal Process., 2011
Fast global convergence of gradient methods for high-dimensional statistical recovery
CoRR, 2011
A More Powerful Two-Sample Test in High Dimensions using Random Projection.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011
High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity.
Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011
Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions.
Proceedings of the 28th International Conference on Machine Learning, 2011
Early stopping for non-parametric regression: An optimal data-dependent stopping rule.
Proceedings of the 49th Annual Allerton Conference on Communication, 2011
Stochastic belief propagation: Low-complexity message-passing with guarantees.
Proceedings of the 49th Annual Allerton Conference on Communication, 2011
2010
Information-theoretic limits on sparse signal recovery: dense versus sparse measurement matrices.
IEEE Trans. Inf. Theory, 2010
Lossy source compression using low-density generator matrix codes: analysis and algorithms.
IEEE Trans. Inf. Theory, 2010
Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization.
IEEE Trans. Inf. Theory, 2010
Analysis of absorbing sets and fully absorbing sets of array-based LDPC codes.
IEEE Trans. Inf. Theory, 2010
Network coding for distributed storage systems.
IEEE Trans. Inf. Theory, 2010
An Efficient 10GBASE-T Ethernet LDPC Decoder Design With Low Error Floors.
IEEE J. Solid State Circuits, 2010
Message-passing for Graph-structured Linear Programs: Proximal Methods and Rounding Schemes.
J. Mach. Learn. Res., 2010
Restricted Eigenvalue Properties for Correlated Gaussian Designs.
J. Mach. Learn. Res., 2010
High-dimensional Variable Selection with Sparse Random Projections: Measurement Sparsity and Statistical Efficiency.
J. Mach. Learn. Res., 2010
Distributed Dual Averaging In Networks.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010
Fast global convergence rates of gradient methods for high-dimensional statistical recovery.
Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010
A near-optimal algorithm for network-constrained averaging with noisy links.
Proceedings of the IEEE International Symposium on Information Theory, 2010
Information-theoretic bounds on model selection for Gaussian Markov random fields.
Proceedings of the IEEE International Symposium on Information Theory, 2010
Estimation of (near) low-rank matrices with noise and high-dimensional scaling.
Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010
Lossy source coding with sparse graph codes: A variational formulation of soft decimation.
Proceedings of the 48th Annual Allerton Conference on Communication, 2010
2009
Low-Density Graph Codes That Are Optimal for Binning and Coding With Side Information.
IEEE Trans. Inf. Theory, 2009
Information-theoretic limits on sparsity recovery in the high-dimensional and noisy setting.
IEEE Trans. Inf. Theory, 2009
Sharp thresholds for high-dimensional and noisy sparsity recovery using l1-constrained quadratic programming (Lasso).
IEEE Trans. Inf. Theory, 2009
Guessing facets: polytope structure and improved LP decoder.
IEEE Trans. Inf. Theory, 2009
Design of LDPC decoders for improved low error rate performance: quantization and algorithm choices.
IEEE Trans. Commun., 2009
Predicting error floors of structured LDPC codes: deterministic bounds and estimates.
IEEE J. Sel. Areas Commun., 2009
Simultaneous support recovery in high dimensions: Benefits and perils of block l<sub>1</sub>/l<sub>infinity</sub>-regularization
CoRR, 2009
Minimax rates of estimation for high-dimensional linear regression over $\ell_q$-balls.
CoRR, 2009
Lower bounds on minimax rates for nonparametric regression with additive sparsity and smoothness.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009
A unified framework for high-dimensional analysis of $M$-estimators with decomposable regularizers.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009
Information-theoretic lower bounds on the oracle complexity of convex optimization.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009
Minimax rates of convergence for high-dimensional regression under ℓq-ball sparsity.
Proceedings of the 47th Annual Allerton Conference on Communication, 2009
2008
Convergence Analysis of Reweighted Sum-Product Algorithms.
IEEE Trans. Signal Process., 2008
Geographic Gossip: Efficient Averaging for Sensor Networks.
IEEE Trans. Signal Process., 2008
On Optimal Quantization Rules for Some Problems in Sequential Decentralized Detection.
IEEE Trans. Inf. Theory, 2008
Probabilistic Analysis of Linear Programming Decoding.
IEEE Trans. Inf. Theory, 2008
Graphical Models, Exponential Families, and Variational Inference.
Found. Trends Mach. Learn., 2008
Lower Bounds on the Rate-Distortion Function of LDGM Codes
CoRR, 2008
High-dimensional subset recovery in noise: Sparsified measurements without loss of statistical efficiency
CoRR, 2008
Model Selection in Gaussian Graphical Models: High-Dimensional Consistency of l<sub>1</sub>-regularized MLE.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008
High-dimensional support union recovery in multivariate regression.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008
Phase transitions for high-dimensional joint support recovery.
Proceedings of the Advances in Neural Information Processing Systems 21, 2008
Information-theoretic limits on sparse support recovery: Dense versus sparse measurements.
Proceedings of the 2008 IEEE International Symposium on Information Theory, 2008
Information-theoretic limits of graphical model selection in high dimensions.
Proceedings of the 2008 IEEE International Symposium on Information Theory, 2008
High-dimensional subset recovery in noise: Sparse measurements and statistical efficiency.
Proceedings of the 2008 IEEE International Symposium on Information Theory, 2008
Error floors in LDPC codes: Fast simulation, bounds and hardware emulation.
Proceedings of the 2008 IEEE International Symposium on Information Theory, 2008
High-dimensional analysis of semidefinite relaxations for sparse principal components.
Proceedings of the 2008 IEEE International Symposium on Information Theory, 2008
Message-passing for graph-structured linear programs: proximal projections, convergence and rounding schemes.
Proceedings of the Machine Learning, 2008
Lowering LDPC Error Floors by Postprocessing.
Proceedings of the Global Communications Conference, 2008. GLOBECOM 2008, New Orleans, LA, USA, 30 November, 2008
Spectral clustering in high-dimensions: Necessary and sufficient conditions for dense and sparse mixtures.
Proceedings of the 46th Annual Allerton Conference on Communication, 2008
Sample complexity of determining structures of graphical models.
Proceedings of the 46th Annual Allerton Conference on Communication, 2008
Union support recovery in high-dimensional multivariate regression.
Proceedings of the 46th Annual Allerton Conference on Communication, 2008
2007
LP Decoding Corrects a Constant Fraction of Errors.
IEEE Trans. Inf. Theory, 2007
Sparse Graph Codes for Side Information and Binning.
IEEE Signal Process. Mag., 2007
A new look at survey propagation and its generalizations.
J. ACM, 2007
Guessing Facets: Polytope Structure and Improved LP Decoding
CoRR, 2007
Universal Quantile Estimation with Feedback in the Communication-Constrained Setting
CoRR, 2007
Low-density graph codes that are optimal for source/channel coding and binning
CoRR, 2007
Loop Series and Bethe Variational Bounds in Attractive Graphical Models.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007
Estimating divergence functionals and the likelihood ratio by penalized convex risk minimization.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007
Information-theoretic bounds on sparsity recovery in the high-dimensional and noisy setting.
Proceedings of the IEEE International Symposium on Information Theory, 2007
Nonparametric estimation of the likelihood ratio and divergence functionals.
Proceedings of the IEEE International Symposium on Information Theory, 2007
Robust message-passing for statistical inference in sensor networks.
Proceedings of the 6th International Conference on Information Processing in Sensor Networks, 2007
Network Coding for Distributed Storage Systems.
Proceedings of the INFOCOM 2007. 26th IEEE International Conference on Computer Communications, 2007
Quantization Effects in Low-Density Parity-Check Decoders.
Proceedings of IEEE International Conference on Communications, 2007
Analysis of Absorbing Sets for Array-Based LDPC Codes.
Proceedings of IEEE International Conference on Communications, 2007
2006
Log-determinant relaxation for approximate inference in discrete Markov random fields.
IEEE Trans. Signal Process., 2006
Distributed fusion in sensor networks.
IEEE Signal Process. Mag., 2006
Data association based on optimization in graphical models with application to sensor networks.
Math. Comput. Model., 2006
Estimating the "Wrong" Graphical Model: Benefits in the Computation-Limited Setting.
J. Mach. Learn. Res., 2006
On optimal quantization rules for some sequential decision problems
CoRR, 2006
Sharp thresholds for high-dimensional and noisy recovery of sparsity
CoRR, 2006
Inconsistent parameter estimation in Markov random fields: Benefits in the computation-limited setting
CoRR, 2006
Analysis of LDGM and compound codes for lossy compression and binning
CoRR, 2006
Low density codes achieve the rate-distortion bound
CoRR, 2006
High-Dimensional Graphical Model Selection Using ℓ<sub>1</sub>-Regularized Logistic Regression.
Proceedings of the Advances in Neural Information Processing Systems 19, 2006
Low-density constructions for lossy compression, binning, and coding with side information.
Proceedings of the 2006 IEEE Information Theory Workshop, 2006
Universal Quantile Estimation with Feedback in the Communication-Constrained Setting.
Proceedings of the Proceedings 2006 IEEE International Symposium on Information Theory, 2006
On optimal quantization rules for sequential decision problems.
Proceedings of the Proceedings 2006 IEEE International Symposium on Information Theory, 2006
Low-density constructions can achieve the Wyner-Ziv and Gelfand-Pinsker bounds.
Proceedings of the Proceedings 2006 IEEE International Symposium on Information Theory, 2006
Guessing Facets: Polytope Structure and Improved LP Decoder.
Proceedings of the Proceedings 2006 IEEE International Symposium on Information Theory, 2006
Geographic gossip: efficient aggregation for sensor networks.
Proceedings of the Fifth International Conference on Information Processing in Sensor Networks, 2006
Investigation of Error Floors of Structured Low-Density Parity-Check Codes by Hardware Emulation.
Proceedings of the Global Telecommunications Conference, 2006. GLOBECOM '06, San Francisco, CA, USA, 27 November, 2006
Low Density Codes Achieve theRate-Distortion Bound.
Proceedings of the 2006 Data Compression Conference (DCC 2006), 2006
2005
Nonparametric decentralized detection using kernel methods.
IEEE Trans. Signal Process., 2005
MAP estimation via agreement on trees: message-passing and linear programming.
IEEE Trans. Inf. Theory, 2005
A new class of upper bounds on the log partition function.
IEEE Trans. Inf. Theory, 2005
Using linear programming to Decode Binary linear codes.
IEEE Trans. Inf. Theory, 2005
On divergences, surrogate loss functions, and decentralized detection
CoRR, 2005
MAP estimation via agreement on (hyper)trees: Message-passing and linear programming
CoRR, 2005
On the Optimality of Tree-reweighted Max-product Message-passing.
Proceedings of the UAI '05, 2005
Estimating the wrong Markov random field: Benefits in the computation-limited setting.
Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005
Divergences, surrogate loss functions and experimental design.
Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005
Lossy source encoding via message-passing and decimation over generalized codewords of LDGM codes.
Proceedings of the 2005 IEEE International Symposium on Information Theory, 2005
2004
Embedded trees: estimation of Gaussian Processes on graphs with cycles.
IEEE Trans. Signal Process., 2004
Tree consistency and bounds on the performance of the max-product algorithm and its generalizations.
Stat. Comput., 2004
Decentralized detection and classification using kernel methods.
Proceedings of the Machine Learning, 2004
2003
Tree-based reparameterization framework for analysis of sum-product and related algorithms.
IEEE Trans. Inf. Theory, 2003
Image denoising using scale mixtures of Gaussians in the wavelet domain.
IEEE Trans. Image Process., 2003
Semidefinite Relaxations for Approximate Inference on Graphs with Cycles.
Proceedings of the Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems, 2003
Tree-reweighted belief propagation algorithms and approximate ML estimation by pseudo-moment matching.
Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, 2003
2002
Stochastic processes on graphs with cycles: geometric and variational approaches.
PhD thesis, 2002
Statistical and Information-Theoretic Methods for Self-Organization and Fusion of Multimodal, Networked Sensors.
Int. J. High Perform. Comput. Appl., 2002
Exact MAP Estimates by (Hyper)tree Agreement.
Proceedings of the Advances in Neural Information Processing Systems 15 [Neural Information Processing Systems, 2002
2001
Tree-based reparameterization for approximate inference on loopy graphs.
Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001
Adaptive Wiener denoising using a Gaussian scale mixture model in the wavelet domain.
Proceedings of the 2001 International Conference on Image Processing, 2001
2000
Tree-Based Modeling and Estimation of Gaussian Processes on Graphs with Cycles.
Proceedings of the Advances in Neural Information Processing Systems 13, 2000
Random Cascades of Gaussian Scale Mixtures and Their Use in Modeling Natural Images With Application to Denoising.
Proceedings of the 2000 International Conference on Image Processing, 2000
1999
Scale Mixtures of Gaussians and the Statistics of Natural Images.
Proceedings of the Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29, 1999