Teaching and compressing for low VC-dimension

@article{Moran2015TeachingAC,
  title={Teaching and compressing for low VC-dimension},
  author={Shay Moran and Amir Shpilka and Avi Wigderson and Amir Yehudayoff},
  journal={Electronic Colloquium on Computational Complexity (ECCC)},
  year={2015},
  volume={22},
  pages={25}
}
In this work we study the quantitative relation between VC-dimension and two other basic parameters related to learning and teaching. Namely, the quality of sample compression schemes and of teaching sets for classes of low VC-dimension. Let $C$ be a binary concept class of size $m$ and VC-dimension $d$. Prior to this work, the best known upper bounds for both parameters were $\log(m)$, while the best lower bounds are linear in $d$. We present significantly better upper bounds on both as… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-8 OF 8 CITATIONS

Optimal Collusion-Free Teaching

VIEW 11 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Proper PAC learning is compressing

  • Electronic Colloquium on Computational Complexity
  • 2015
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Sample compression schemes for VC classes

  • 2016 Information Theory and Applications Workshop (ITA)
  • 2015
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Compressing and Teaching for Low VC-Dimension

  • 2015 IEEE 56th Annual Symposium on Foundations of Computer Science
  • 2015
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 43 REFERENCES

On Weak Learning

  • J. Comput. Syst. Sci.
  • 1995
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

On the complexity of teaching

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Space-bounded learning and the vapnik-chervonenkis dimension

S. Floyd
  • COLT, pages 349–364
  • 1989
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Teachability in computational learning

  • New Generation Computing
  • 1990
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…