Corpus ID: 49554472

Local moment matching: A unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance

@inproceedings{Han2018LocalMM,
  title={Local moment matching: A unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance},
  author={Y. Han and J. Jiao and T. Weissman},
  booktitle={COLT},
  year={2018}
}
  • Y. Han, J. Jiao, T. Weissman
  • Published in COLT 2018
  • Mathematics, Computer Science
  • We present \emph{Local Moment Matching (LMM)}, a unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance. We construct an efficiently computable estimator that achieves the minimax rates in estimating the distribution up to permutation, and show that the plug-in approach of our unlabeled distribution estimator is "universal" in estimating symmetric functionals of discrete distributions. Instead of doing best polynomial approximation… CONTINUE READING
    35 Citations

    Topics from this paper

    A General Framework for Symmetric Property Estimation
    • 5
    • PDF
    Unified Sample-Optimal Property Estimation in Near-Linear Time
    • Highly Influenced
    • PDF
    Unified Sample-Optimal Property Estimation in Near-Linear Time
    • Highly Influenced
    • PDF
    Unified Sample-Optimal Property Estimation in Near-Linear Time
    • 1
    • Highly Influenced
    Efficient profile maximum likelihood for universal symmetric property estimation
    • 23
    • PDF
    Unified Sample-Optimal Property Estimation in Near-Linear Time
    • 12
    • Highly Influenced
    • PDF
    The Broad Optimality of Profile Maximum Likelihood
    • Highly Influenced
    • PDF
    The Broad Optimality of Profile Maximum Likelihood
    • 2
    • Highly Influenced
    • PDF
    Profile Entropy: A Fundamental Measure for the Learnability and Compressibility of Discrete Distributions
    • 6
    • PDF

    References

    SHOWING 1-10 OF 56 REFERENCES
    Minimax estimation of discrete distributions
    • Y. Han, J. Jiao, T. Weissman
    • Mathematics, Computer Science
    • 2015 IEEE International Symposium on Information Theory (ISIT)
    • 2015
    • 12
    Minimax Estimation of Functionals of Discrete Distributions
    • 193
    • PDF
    A Unified Maximum Likelihood Approach for Optimal Distribution Property Estimation
    • 13
    • Highly Influential
    • PDF
    Minimax Estimation of KL Divergence between Discrete Distributions
    • 16
    • PDF
    Minimax estimation of the L1 distance
    • J. Jiao, Y. Han, T. Weissman
    • Mathematics, Computer Science
    • 2016 IEEE International Symposium on Information Theory (ISIT)
    • 2016
    • 55
    Optimal rates of entropy estimation over Lipschitz balls
    • 40
    • PDF
    Approximate Profile Maximum Likelihood
    • 35
    • PDF
    On estimation of the Lr norm of a regression function
    • 72
    • PDF
    The Power of Linear Estimators
    • G. Valiant, Paul Valiant
    • Mathematics, Computer Science
    • 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science
    • 2011
    • 136
    • Highly Influential
    • PDF
    Estimating the Unseen: Improved Estimators for Entropy and other Properties
    • 40