We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
Sanjoy Dasgupta, Adam Tauman Kalai, Claire Montele...
Another hybrid conjugate gradient algorithm is subject to analysis. The parameter k is computed as a convex combination of HS k (Hestenes-Stiefel) and DY k (Dai-Yuan) algorithms, i...
Identifying and controlling bias is a key problem in empirical sciences. Causal diagram theory provides graphical criteria for deciding whether and how causal effects can be iden...
We address a fundamental problem arising from analysis of biomolecular sequences. The input consists of two numbers wmin and wmax and a sequence S of n number pairs (ai, wi) with ...
Backward beam search for dependency analysis of Japanese is proposed. As dependencies normally go from left to right in Japanese, it is effective to analyze sentences backwards (f...