The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings

@inproceedings{Choromanski2017TheUE,
  title={The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings},
  author={Krzysztof Choromanski and Mark Rowland and Adrian Weller},
  booktitle={NIPS},
  year={2017}
}
We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the JohnsonLindenstrauss transform and the angular kernel, we show that we can select matrices yielding guaranteed improved performance in accuracy and/or speed compared to earlier methods. We introduce matrices with complex entries which give significant further accuracy… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
8 Citations
21 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Generalized spectral kernels

  • Y.-L.K. Samo, S. Roberts
  • CoRR, abs/1506.02236,
  • 2015
3 Excerpts

Similar Papers

Loading similar papers…