: This paper introduces a tailored procedure model to construct reference models by using rich empirical data. The procedure model has been built based on requirements from the pub...
This paper presents the first Rademacher complexity-based error bounds for noni.i.d. settings, a generalization of similar existing bounds derived for the i.i.d. case. Our bounds ...
We describe a primal-dual framework for the design and analysis of online strongly convex optimization algorithms. Our framework yields the tightest known logarithmic regret bound...
Neuroimaging datasets often have a very large number of voxels and a very small number of training cases, which means that overfitting of models for this data can become a very se...
Tanya Schmah, Geoffrey E. Hinton, Richard S. Zemel...
We present a generative model for performing sparse probabilistic projections, which includes sparse principal component analysis and sparse canonical correlation analysis as spec...