All Publications

  • 2017
  • Deep Active Learning for Named Entity Recognition, ACL Workshop on Representation Learning for NLP, 2017. arxiv poster
  • Tensor Contraction Layers for Parsimonious Deep Nets, CVPR Workshop, 2017. arxiv slides
  • Spectral Latent Dirichlet Allocation model on Spark, 2017. whitepaper github
  • Reinforcement Learning in Rich-Observation MDPs using Spectral Methods, RLDM 2017. pdf poster
  • Homotopy Analysis for Tensor PCA, COLT 2017. arxiv slides
  • Spectral Methods for Correlated Topic Models, AISTATS 2017. url arxiv code poster
  • 2016
  • Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization, SIAM J. Optim., 26(4), 2016. url
  • Experimental results: Reinforcement Learning of POMDPs using Spectral Methods, NIPS 2016 Workshop on Deep RL. pdf poster
  • Online and Differentially-Private Tensor Decomposition, NIPS 2016. pdf
  • Tensor Contractions with Extended BLAS Kernels on CPU and GPU, HiPC 2016. arxiv poster blog post
  • PhD Thesis: Stochastic Optimization in High Dimension, Hanie Sedghi, 2016. pdf
  • PhD Thesis: Discovery of Latent Factors in High-dimensional Data Using Tensor Methods, Furong Huang, 2016. arxiv
  • PhD Thesis: Non-convex Optimization in Machine Learning: Provable Guarantees Using Tensor Methods, Majid Janzamin, 2016. pdf
  • Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies, COLT 2016. pdf talk slides
  • Unsupervised Learning of Word-Sequence Representations from Scratch via Convolutional Tensor Decomposition, ACL 2016. pdf slides
  • Training Input-Output Recurrent Neural Networks through Spectral Methods, 2016. pdf
  • Reinforcement Learning of POMDPs using Spectral Methods, COLT 2016. pdf talk slides
  • Efficient approaches for escaping higher order saddle points in non-convex optimization, COLT 2016. arxiv blog post
  • Provable Tensor Methods for Learning Mixtures of Generalized Linear Models, AISTATS 2016. url
  • Tensor vs Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations, AISTATS 2016. pdf poster slides
  • 2015
  • Feast at Play: Feature ExtrAction using Score function Tensors, NIPS 2015. url
  • Convolutional Dictionary Learning through Tensor Factorization, NIPS 2015. url slides code
  • Scalable Latent Tree Model and its Application to Health Analytics, NIPS 2015. arxiv slides
  • Discovering Neuronal Cell Types and Their Gene Expression Profiles Using a Spatial Point Process Mixture Model, NIPS 2015. arxiv
  • Are You Going to the Party: Depends, Who Else is Coming?: [Learning Hidden Group Dynamics via Conditional Latent Tree Models], ICDM 2015. url code
  • Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models, SUNw 2015. arxiv
  • Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Method, 2015. pdf slides talk
  • Fast and Guaranteed Tensor Decomposition via Sketching, NIPS 2015. arxiv slides
  • A Scale Mixture Perspective of Multiplicative Noise in Neural Networks, 2015. arxiv
  • Learning Mixed Membership Community Models in Social Tagging Networks through Tensor Methods, 2015. pdf
  • 2014
  • Online Tensor Methods for Learning Latent Variable Models, JMLR 2014. pdf
  • Score Function Features for Discriminative Learning: Matrix and Tensor Framework, 2014. pdf
  • Provable Methods for Training Neural Networks with Sparse Connectivity, NIPS 2014. pdf
  • Analyzing Tensor Power Method Dynamics in Overcomplete Regime, 2014. pdf
  • Non-convex Robust PCA, NIPS 2014. pdf slides
  • Sample Complexity Analysis for Learning Overcomplete Latent Variable Models through Tensor Methods, 2014. pdf abridged slides
  • Multi-Step Stochastic ADMM in High Dimensions: Applications in Sparse Optimization and Noisy Matrix Decomposition, NIPS 2014. url talk
  • Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank-1 Updates, 2014. pdf slides code
  • Nonparametric Estimation of Multi-View Latent Variable Models, ICML 2014. pdf
  • Tensor Decompositions for Learning Latent Variable Models, JMLR 2014. pdf blog post
  • 2013
  • Learning Loopy Graphical Models with Latent Variables: Efficient Methods and Guarantees, Ann. Statist., 41(2), 2013. pdf supplement slides code
  • Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization, 2013. pdf slides
  • Exact Recovery of Sparsely Used Overcomplete Dictionaries, 2013. pdf
  • When Are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity, 2013. pdf
  • A Tensor Spectral Approach to Learning Mixed Membership Community Models, COLT 2013. pdf slides
  • Learning Latent Bayesian Networks and Topic Models Under Expansion Constraints, ICML 2013. pdf
  • Fast, Concurrent and Distributed Load Balancing under Switching Costs and Imperfect Observations, IEEE INFOCOM 2013. pdf
  • 2012
  • High-Dimensional Structure Learning of Ising Models: Local Separation Criterion, Ann. Statist. 40(3), 2012. pdf supplement code slides
  • Learning Linear Bayesian Networks with Latent Variables, 2012. pdf
  • Feedback Message Passing for Inference in Gaussian Graphical Models, IEEE Trans. on Signal Processing, 60(8), 2012. pdf
  • High-Dimensional Covariance Decomposition into Sparse Markov and Independence Domains, ICML 2012. pdf pdf slides
  • A Method of Moments for Mixture Models and Hidden Markov Models, COLT 2012. pdf pdf
  • Learning High-Dimensional Mixtures of Graphical Models, NIPS 2012. pdf pdf
  • Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation, NIPS 2012. pdf pdf
  • 2011
  • High-Dimensional Gaussian Graphical Model Selection: Walk-Summability and Local Separation Criterion, JMLR 13:229-337, 2012. NIPS 2011. pdf pdf talk slides
  • High-Dimensional Graphical Model Selection: Tractable Graph Families and Necessary Conditions, NIPS 2011. pdf
  • Spectral Methods for Learning Multivariate Latent Tree Structure, NIPS 2011. arxiv
  • Robust Rate Maximization Game Under Bounded Channel Uncertainty, IEEE Trans. Vehicular Technology, 60:9, 2011. pdf
  • Summary Based Structures with Improved Sublinear Recovery for Compressed Sensing, IEEE ISIT 2011. pdf
  • Topology Discovery of Sparse Random Graphs With Few Participants, ACM SIGMETRICS 2011. pdf pdf slides
  • Learning Latent Tree Graphical Models, JMLR 2011. pdf project homepage Allerton version Allerton slides seminar slides
  • Learning High-Dimensional Markov Forest Distributions: Analysis of Error Rates, JMLR 2011. pdf Allerton version Allerton slides
  • Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret, IEEE JSAC 2011. pdf
  • Energy-Latency Tradeoff for In-Network Function Computation in Random Networks, IEEE INFOCOM 2011. pdf slides
  • Index-Based Sampling Policies for Tracking Dynamic Networks under Sampling Constraints, IEEE INFOCOM 2011. pdf supplemental material
  • A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures, IEEE Trans. Information Theory,57:3, 2011. pdf
  • 2010
  • Scaling Laws for Random Spatial Graphical Models, IEEE ISIT 2010. pdf slides
  • Error Exponents for Composite Hypothesis Testing of Markov Forest Distributions, IEEE ISIT 2010. pdf slides proofs
  • Learning Gaussian Tree Models: Analysis of Error Exponents and Extremal Structures, IEEE Trans. Signal Processing, 58:5, 2010. pdf slides
  • Robust Rate Maximization Game Under Bounded Channel Uncertainty, IEEE ICASSP 2010. pdf
  • Opportunistic Spectrum Access with Multiple Users: Learning under Competition, IEEE INFOCOM 2010. pdf slides
  • Seeing Through Black Boxes : Tracking Transactions through Queues under Monitoring Resource Constraints, Elsevier Performance Evaluation 2010. pdf
  • 2009
  • Energy Scaling Laws for Distributed Inference in Random Fusion Networks, IEEE JSAC, 27:7, 2009. pdf
  • Selectively Retrofitting Monitoring in Distributed Systems, Workshop on MAMA 2009. pdf
  • Detection Error Exponent for Spatially Dependent Samples in Random Networks, IEEE ISIT 2009. pdf
  • Prize-Collecting Data Fusion for Cost-Performance Tradeoff in Distributed Inference, IEEE INFOCOM 2009. pdf tech report
  • Detection of Gauss-Markov random fields with nearest-neighbor dependency, IEEE Trans. Information Theory, 55:2, 2009. pdf
  • 2008 and Earlier
  • Optimal Node Density for Detection in Energy Constrained Random Networks, IEEE Trans. Signal Processing, 56:10, 2008. pdf
  • Distributed Estimation Via Random Access, IEEE Trans. Information Theory, 54:7, 2008. pdf
  • Tracking in a Spaghetti Bowl: Monitoring Transactions Using Footprints, ACM SIGMETRICS 2008. pdf
  • Minimum Cost Data Aggregation with Localized Processing for Statistical Inference, IEEE INFOCOM 2008. pdf
  • A Large Deviation Analysis of Detection over Multi-Access Channels with Random Number of Sensors, ICASSP 2006 (Best Paper Award). pdf