Corpus ID: 58491286

On Testing of Samplers

@article{Chakraborty2020OnTO,
  title={On Testing of Samplers},
  author={Sourav Chakraborty and Kuldeep S. Meel},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.12918}
}
  • Sourav Chakraborty, Kuldeep S. Meel
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • Given a set of items $\mathcal{F}$ and a weight function $\mathtt{wt}: \mathcal{F} \mapsto (0,1)$, the problem of sampling seeks to sample an item proportional to its weight. Sampling is a fundamental problem in machine learning. The daunting computational complexity of sampling with formal guarantees leads designers to propose heuristics-based techniques for which no rigorous theoretical analysis exists to quantify the quality of generated distributions. This poses a challenge in designing a… CONTINUE READING

    Tables from this paper

    References

    SHOWING 1-10 OF 41 REFERENCES
    Learning and Testing Junta Distributions with Subcube Conditioning
    • 2
    • PDF
    WAPS: Weighted and Projected Sampling
    • 7
    • PDF
    A Chasm Between Identity and Equivalence Testing with Conditional Queries
    • 17
    • Highly Influential
    • PDF
    Distribution-Aware Sampling and Weighted Model Counting for SAT
    • 109
    • PDF
    Anaconda: A Non-Adaptive Conditional Sampling Algorithm for Distribution Testing
    • 8
    • PDF
    Testing probability distributions using conditional samples
    • 44
    • Highly Influential
    • PDF
    On the power of conditional samples in distribution testing
    • 31
    • Highly Influential
    • PDF
    Property Testing of Joint Distributions using Conditional Samples
    • 10
    • PDF
    Testing Conditional Independence of Discrete Distributions
    • 24
    • PDF
    On Testing of Uniform Samplers
    • 7
    • PDF