Abstract | ||
---|---|---|
A kernel over the Boolean domain is said to be reflection-invariant, if its value does not change when we flip the same bit in both arguments. (Many popular kernels have this property.) We study the geo- metric margins that can be achieved when we represent a specific Boolean function f by a classifier that employs a reflection- invariant kernel. It turns out k ˆ fk ∞ is an |
Year | Venue | Keywords |
---|---|---|
2008 | COLT | boolean function |
Field | DocType | Citations |
Kernel (linear algebra),Boolean function,Discrete mathematics,Mathematical optimization,Invariant (physics),Generalization,Upper and lower bounds,Parity function,Invariant (mathematics),Mathematics,Boolean domain | Conference | 0 |
PageRank | References | Authors |
0.34 | 15 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thorsten Doliwa | 1 | 34 | 2.39 |
Michael Kallweit | 2 | 10 | 1.50 |
Hans-Ulrich Simon | 3 | 567 | 104.52 |
andrew mccallum | 4 | 0 | 0.34 |