Nearly Tight Bounds on ℓ1 Approximation of Self-Bounding Functions
@article{Feldman2014NearlyTB, title={Nearly Tight Bounds on ℓ1 Approximation of Self-Bounding Functions}, author={V. Feldman and Pravesh Kothari and J. Vondr{\'a}k}, journal={ArXiv}, year={2014}, volume={abs/1404.4702} }
We study the complexity of learning and approximation of self-bounding functions over the uniform distribution on the Boolean hypercube ${0,1}^n$. Informally, a function $f:{0,1}^n \rightarrow \mathbb{R}$ is self-bounding if for every $x \in {0,1}^n$, $f(x)$ upper bounds the sum of all the $n$ marginal decreases in the value of the function at $x$. Self-bounding functions include such well-known classes of functions as submodular and fractionally-subadditive (XOS) functions. They were… CONTINUE READING
Topics from this paper
2 Citations
Tight Bounds on Low-Degree Spectral Concentration of Submodular and XOS Functions
- Mathematics, Computer Science
- 2015 IEEE 56th Annual Symposium on Foundations of Computer Science
- 2015
- 12
- PDF
References
SHOWING 1-10 OF 55 REFERENCES
Representation, Approximation and Learning of Submodular Functions Using Low-rank Decision Trees
- Mathematics, Computer Science
- COLT
- 2013
- 26
- PDF
Approximate resilience, monotonicity, and the complexity of agnostic learning
- Mathematics, Computer Science
- SODA
- 2015
- 17
- PDF
Learning Coverage Functions and Private Release of Marginals
- Mathematics, Computer Science
- COLT
- 2014
- 31
- PDF
Optimal Bounds on Approximation of Submodular and XOS Functions by Juntas
- Mathematics, Computer Science
- 2013 IEEE 54th Annual Symposium on Foundations of Computer Science
- 2013
- 22
- PDF
Tight Bounds on Low-Degree Spectral Concentration of Submodular and XOS Functions
- Mathematics, Computer Science
- 2015 IEEE 56th Annual Symposium on Foundations of Computer Science
- 2015
- 12
- PDF
Bounded Independence Fools Halfspaces
- Mathematics, Computer Science
- 2009 50th Annual IEEE Symposium on Foundations of Computer Science
- 2009
- 18
- PDF