Lower Bounds on Learning Random Structures with Statistical Queries

13 years 5 months ago

Download www.cc.gatech.edu

We show that random DNF formulas, random log-depth decision trees and random deterministic finite acceptors cannot be weakly learned with a polynomial number of statistical queries with respect to an arbitrary distribution on examples.

Dana Angluin, David Eisenstat, Leonid Kontorovich,

Real-time Traffic

ALT 2010 | Log-depth Decision Trees | Machine Learning | Random Deterministic Finite | Random Dnf Formulas |

claim paper

» On Using Extended Statistical Queries to Avoid Membership Queries

» Lower Bounds and Hardness Amplification for Learning Shallow Monotone Formulas

» Efficient Learning Algorithms Yield Circuit Lower Bounds

» Unconditional lower bounds for learning intersections of halfspaces

» Learning and Lower Bounds for AC0 with Threshold Gates

» A Geometric Approach to Lower Bounds for Approximate NearNeighbor Search and Partial Match

» Higher Lower Bounds for NearNeighbor and Further Rich Problems

» A Bound on the Performance of LDA in Randomly Projected Data Spaces

Post Info
More Details (n/a)

Added	26 Oct 2010
Updated	26 Oct 2010
Type	Conference
Year	2010
Where	ALT
Authors	Dana Angluin, David Eisenstat, Leonid Kontorovich, Lev Reyzin

Comments (0)

Sciweavers

Lower Bounds on Learning Random Structures with Statistical Queries

ALT 2010 | Log-depth Decision Trees | Machine Learning | Random Deterministic Finite | Random Dnf Formulas |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers