Most machine learning algorithms share the following drawback: they only output bare predictions but not the con dence in those predictions. In the 1960s algorithmic information t...
This paper extends the analysis of Pollard’s rho algorithm for solving a single instance of the discrete logarithm problem in a finite cyclic group G to the case of solving more...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
We describe a simple random-sampling based procedure for producing sparse matrix approximations. Our procedure and analysis are extremely simple: the analysis uses nothing more th...