Corpus ID: 11206025

Provable Algorithms for Inference in Topic Models

@article{Arora2016ProvableAF,
  title={Provable Algorithms for Inference in Topic Models},
  author={Sanjeev Arora and R. Ge and F. Koehler and Tengyu Ma and A. Moitra},
  journal={ArXiv},
  year={2016},
  volume={abs/1605.08491}
}
  • Sanjeev Arora, R. Ge, +2 authors A. Moitra
  • Published 2016
  • Computer Science, Mathematics
  • ArXiv
  • Recently, there has been considerable progress on designing algorithms with provable guarantees -- typically using linear algebraic methods -- for parameter learning in latent variable models. But designing provable algorithms for inference has proven to be more challenging. Here we take a first step towards provable inference in topic models. We leverage a property of topic models that enables us to construct simple linear estimators for the unknown topic proportions that have small variance… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Prior-aware Dual Decomposition: Document-specific Topic Inference for Spectral Topic Models
    Provable benefits of representation learning
    8
    Models and algorithms for episodic time-series
    Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
    6
    Learning a Mixture of Two Multinomial Logits
    12
    Learning Networked Exponential Families with Network Lasso

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES
    A Practical Algorithm for Topic Modeling with Provable Guarantees
    298
    Efficient methods for topic model inference on streaming document collections
    381
    Latent Dirichlet Allocation
    23586
    Finding scientific topics
    4722
    Settling the Polynomial Learnability of Mixtures of Gaussians
    246
    Using mixture models for collaborative filtering
    78
    Provable Bounds for Learning Some Deep Representations
    244
    Confidence intervals and hypothesis testing for high-dimensional regression
    449
    A tensor approach to learning mixed membership community models
    118
    Learning Mixtures of Gaussians in High Dimensions
    72