Anima Anandkumar

Sort by:

Tensor decompositions for learning latent variable models

Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade, Matus Telgarsky
Journal of Machine Learning Research
2014

This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models—including Gaussian mixture models, hidden Markov models, and… (More)

Learning Latent Tree Graphical Models

Myung Jin Choi, Vincent Y. F. Tan, Anima Anandkumar, Alan S. Willsky
Journal of Machine Learning Research
2011

We study the problem of learning a latent tree graphical model where samples are available only from a subset of variables. We propose two consistent and computationally efficient algorithms for… (More)

A Method of Moments for Mixture Models and Hidden Markov Models

Anima Anandkumar, Daniel J. Hsu, Sham M. Kakade
COLT
2012

Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such… (More)

Non-convex Robust PCA

Praneeth Netrapalli, U. N. Niranjan, Sujay Sanghavi, Anima Anandkumar, Prateek Jain
NIPS
2014

We propose a new method for robust PCA – the task of recovering a low-rank matrix from sparse corruptions that are of unknown value and support. Our method involves alternating between projecting… (More)

Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret

Anima Anandkumar, Nithin Michael, Ao Tang, Ananthram Swami
IEEE Journal on Selected Areas in Communications
2011

The problem of distributed learning and channel access is considered in a cognitive network with multiple secondary users. The availability statistics of the channels are initially unknown to the… (More)

A Spectral Algorithm for Latent Dirichlet Allocation

Anima Anandkumar, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Yi-Kai Liu
Algorithmica
2012

Topic modeling is a generalization of clustering that posits that observations (words in a document) are generated by multiple latent factors (topics), as opposed to just one. The increased… (More)

Opportunistic Spectrum Access with Multiple Users: Learning under Competition

Anima Anandkumar, Nithin Michael, Ao Tang
2010 Proceedings IEEE INFOCOM
2010

The problem of cooperative allocation among multiple secondary users to maximize cognitive system throughput is considered. The channel availability statistics are initially unknown to the secondary… (More)

A Tensor Spectral Approach to Learning Mixed Membership Community Models

Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade
COLT
2013

Detecting hidden communities from observed interactions is a classical problem. Theoretical analysis of community detection has so far been mostly limited to models with non-overlapping communities… (More)

Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation

Anima Anandkumar, Dean P. Foster, Daniel J. Hsu, Sham M. Kakade, Yi-Kai Liu
ArXiv
2012

A tensor approach to learning mixed membership community models

Anima Anandkumar, Rong Ge, Daniel J. Hsu, Sham M. Kakade
Journal of Machine Learning Research
2014

Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities… (More)

Filter Results:

Publication Year

Publication Type

Co-author

Journals and Conferences