Extractor-Based Time-Space Lower Bounds for Learning

Sumegha Garg
Sumegha Garg

STOC '18: Symposium on Theory of Computing Los Angeles CA USA June, 2018, pp. 990-1002, 2018.

Cited by: 25|Bibtex|Views19|Links
EI
Keywords:
Branching programstime-space tradeoffextractorslearning from samples

Abstract:

A matrix M: A × X → {−1,1} corresponds to the following learning problem: An unknown element x ∈ X is chosen uniformly at random. A learner tries to learn x from a stream of samples, (a1, b1), (a2, b2) …, where for every i, ai ∈ A is chosen uniformly at random and bi = M(ai,x). Assume that k, l, r are such that any submatrix of M of at ...More

Code:

Data:

Your rating :
0

 

Tags
Comments