Corpus ID: 208201894

On Universal Features for High-Dimensional Learning and Inference

@article{Huang2019OnUF,
  title={On Universal Features for High-Dimensional Learning and Inference},
  author={Shao-Lun Huang and Anuran Makur and Gregory W. Wornell and Lizhong Zheng},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.09105}
}
  • Shao-Lun Huang, Anuran Makur, +1 author Lizhong Zheng
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • We consider the problem of identifying universal low-dimensional features from high-dimensional data for inference tasks in settings involving learning. For such problems, we introduce natural notions of universality and we show a local equivalence among them. Our analysis is naturally expressed via information geometry, and represents a conceptually and computationally useful analysis. The development reveals the complementary roles of the singular value decomposition, Hirschfeld-Gebelein-R… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-9 OF 9 CITATIONS

    An Information-Theoretic Approach to Unsupervised Feature Selection for High-Dimensional Data

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS

    Maximal Correlation Regression

    VIEW 6 EXCERPTS
    CITES BACKGROUND

    An Information Theoretic Interpretation to Deep Neural Networks

    On Universality and Training in Binary Hypothesis Testing

    VIEW 1 EXCERPT
    CITES BACKGROUND

    An Information-Theoretic Approach to Transferability in Task Transfer Learning

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 152 REFERENCES

    An information-theoretic approach to universal feature selection in high-dimensional inference

    VIEW 1 EXCERPT

    Information Bottleneck for Gaussian Variables

    VIEW 2 EXCERPTS

    An efficient algorithm for information decomposition and extraction

    VIEW 1 EXCERPT

    Gaussian Universal Features, Canonical Correlations, and Common Information

    VIEW 1 EXCERPT

    Deep Generalized Canonical Correlation Analysis

    VIEW 1 EXCERPT

    Learning with matrix factorizations

    VIEW 1 EXCERPT