4 search results - page 1 / 1 » Error Bounds for Transductive Learning via Compression and C... |
NIPS
2003
14 years 10 days ago
2003
This paper is concerned with transductive learning. Although transduction appears to be an easier task than induction, there have not been many provably useful algorithms and boun...
ML
2008
ACM
13 years 11 months ago
2008
ACM
Abstract. We consider a large volume principle for transductive learning that prioritizes the transductive equivalence classes according to the volume they occupy in hypothesis spa...
ICML
2006
IEEE
14 years 11 months ago
2006
IEEE
We show that it is possible to use data compression on independently obtained hypotheses from various tasks to algorithmically provide guarantees that the tasks are sufficiently r...
KDD
2009
ACM
14 years 11 months ago
2009
ACM
Mining discrete patterns in binary data is important for subsampling, compression, and clustering. We consider rankone binary matrix approximations that identify the dominant patt...