# Learning DNF Expressions from Fourier Spectrum

@article{Feldman2012LearningDE, title={Learning DNF Expressions from Fourier Spectrum}, author={Vitaly Feldman}, journal={ArXiv}, year={2012}, volume={abs/1203.0594} }

Since its introduction by Valiant in 1984, PAC learning of DNF expressions remains one of the central problems in learning theory. We consider this problem in the setting where the underlying distribution is uniform, or more generally, a product distribution. Kalai, Samorodnitsky and Teng (2009) showed that in this setting a DNF expression can be efficiently approximated from its "heavy" low-degree Fourier coefficients alone. This is in contrast to previous approaches where boosting was used… CONTINUE READING

1

Twitter Mention

#### Topics from this paper.

#### Citations

##### Publications citing this paper.

SHOWING 1-10 OF 14 CITATIONS

## Efficient learning algorithms with limited information

VIEW 2 EXCERPTS

CITES METHODS

## Learning Using Local Membership Queries

VIEW 1 EXCERPT

CITES METHODS

## A Bayesian Framework for Learning Rule Sets for Interpretable Classification

VIEW 1 EXCERPT

CITES BACKGROUND

## Nearly Optimal Solutions for the Chow Parameters Problem and Low-Weight Approximation of Halfspaces

VIEW 1 EXCERPT

CITES METHODS

## A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks

VIEW 1 EXCERPT

CITES METHODS

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 25 REFERENCES

## Weakly learning DNF and characterizing statistical query learning using Fourier analysis

VIEW 9 EXCERPTS

HIGHLY INFLUENTIAL

## Learning and Smoothed Analysis

VIEW 23 EXCERPTS

HIGHLY INFLUENTIAL

## THE SPECTRAL NORM OF FINITE FUNCTIONS

VIEW 2 EXCERPTS

## Boosting and Hard-Core Set Construction

VIEW 2 EXCERPTS

## On the learnability of disjunctive normal form formulas

VIEW 7 EXCERPTS

HIGHLY INFLUENTIAL

## Learning DNF in time 2Õ(n1/3)

VIEW 2 EXCERPTS