Learning Permutations with Exponential Weights

@inproceedings{Helmbold2007LearningPW,
  title={Learning Permutations with Exponential Weights},
  author={D. Helmbold and Manfred K. Warmuth},
  booktitle={COLT},
  year={2007}
}
  • D. Helmbold, Manfred K. Warmuth
  • Published in COLT 2007
  • Mathematics, Computer Science
  • We give an algorithm for learning a permutation on-line. The algorithm maintains its uncertainty about the target permutation as a doubly stochastic matrix. This matrix is updated by multiplying the current matrix entries by exponential factors. These factors destroy the doubly stochastic property of the matrix and an iterative procedure is needed to re-normalize the rows and columns. Even though the result of the normalization procedure does not have a closed form, we can still bound the… CONTINUE READING
    110 Citations
    Online Learning of Permutations Using Extended Formulation
    • PDF
    Sinkhorn Permutation Variational Marginal Inference
    • 1
    • Highly Influenced
    Learning rotations with little regret
    • 8
    • PDF
    Online Linear Optimization over Permutations
    • 36
    • Highly Influenced
    • PDF
    Fourier Theoretic Probabilistic Inference over Permutations
    • 92
    • PDF
    Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension
    • 67
    • PDF
    Learning Probability Distributions over Permutations by Means of Fourier Coefficients
    • 5
    • Highly Influenced
    • PDF
    Learning of Combinatorial Objects via Extended Formulation
    • PDF

    References

    SHOWING 1-10 OF 62 REFERENCES
    Online kernel PCA with entropic matrix updates
    • 25
    • PDF
    Fourier Theoretic Probabilistic Inference over Permutations
    • 92
    • PDF
    Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension
    • 67
    • PDF
    Quadratic Convergence for Scaling of Matrices
    • M. Fürer
    • Computer Science, Mathematics
    • ALENEX/ANALC
    • 2004
    • 5
    • PDF
    Randomized Online PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension
    • 130
    • PDF
    A polynomial-time approximation algorithm for the permanent of a matrix with nonnegative entries
    • 638
    • PDF
    Leaving the Span
    • 28
    • PDF
    ON THE COMPLEXITY OF NONNEGATIVE-MATRIX SCALING
    • 66
    Polynomial approximation algorithms for belief matrix maintenance in identity management
    • 36
    • PDF
    Additive versus exponentiated gradient updates for linear prediction
    • 285
    • PDF