We prove logarithmic regret bounds that depend on the loss L∗ T of the competitor rather than on the number T of time steps. In the general online convex optimization setting, o...
We introduce a novel method for grammatical error correction with a number of small corpora. To make the best use of several corpora with different characteristics, we employ a me...
Hongsuck Seo, Jonghoon Lee, Seokhwan Kim, Kyusong ...
We consider a special type of multi-label learning where class assignments of training examples are incomplete. As an example, an instance whose true class assignment is (c1, c2, ...
Dependency networks approximate a joint probability distribution over multiple random variables as a product of conditional distributions. Relational Dependency Networks (RDNs) are...
Sriraam Natarajan, Tushar Khot, Kristian Kersting,...
—Cross-domain learning methods have shown promising results by leveraging labeled patterns from the auxiliary domain to learn a robust classifier for the target domain which has ...