• Computer Science
  • Published in ICML 2016

Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference

@inproceedings{Achim2016BeyondPC,
  title={Beyond Parity Constraints: Fourier Analysis of Hash Functions for Inference},
  author={Tudor Achim and Ashish Sabharwal and Stefano Ermon},
  booktitle={ICML},
  year={2016}
}
Random projections have played an important role in scaling up machine learning and data mining algorithms. Recently they have also been applied to probabilistic inference to estimate properties of high-dimensional distributions; however, they all rely on the same class of projections based on universal hashing. We provide a general framework to analyze random projections which relates their statistical properties to their Fourier spectrum, which is a well-studied area of theoretical computer… CONTINUE READING

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Closing the gap between short and long xors for model counting

  • Zhao, Shengjia, +5 authors Stefano
  • In Proceedings of AAAI,
  • 2016
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A Scalable Approximate Model Counter

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

A Scalable and Nearly Uniform Generator of SAT Witnesses

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL