Approximate resilience, monotonicity, and the complexity of agnostic learning

@inproceedings{DachmanSoled2015ApproximateRM,
  title={Approximate resilience, monotonicity, and the complexity of agnostic learning},
  author={Dana Dachman-Soled and Vitaly Feldman and Li-Yang Tan and Andrew Wan and Karl Wimmer},
  booktitle={SODA},
  year={2015}
}
  • Dana Dachman-Soled, Vitaly Feldman, +2 authors Karl Wimmer
  • Published in SODA 2015
  • Computer Science, Mathematics
  • A function $f$ is $d$-resilient if all its Fourier coefficients of degree at most $d$ are zero, i.e., $f$ is uncorrelated with all low-degree parities. We study the notion of $\mathit{approximate}$ $\mathit{resilience}$ of Boolean functions, where we say that $f$ is $\alpha$-approximately $d$-resilient if $f$ is $\alpha$-close to a $[-1,1]$-valued $d$-resilient function in $\ell_1$ distance. We show that approximate resilience essentially characterizes the complexity of agnostic learning of a… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 12 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES

    Randomly Supported Independence and Resistance

    The Pattern Matrix Method

    KKL, Kruskal-Katona, and Monotone Nets

    The bit extraction problem or t-resilient functions

    Agnostic Learning of Monomials by Halfspaces Is Hard

    Finding Correlations in Subquadratic Time, with Applications to Learning Parities and Juntas

    • Gregory Valiant
    • Mathematics, Computer Science
    • 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science
    • 2012