News & Updates
Search Research Content
Resource Finder at Kennedy Krieger Institute
A free resource that provides access to information and support for individuals and families living with developmental disabilities.
Error analysis of stochastic gradient descent ranking.
|Title||Error analysis of stochastic gradient descent ranking.|
|Publication Type||Journal Article|
|Year of Publication||2013|
|Authors||Chen H, Tang Y, Li L, Yuan Y, Li X, Tang Y|
|Journal||IEEE transactions on cybernetics|
|Date Published||2013 Jun|
Ranking is always an important task in machine learning and information retrieval, e.g., collaborative filtering, recommender systems, drug discovery, etc. A kernel-based stochastic gradient descent algorithm with the least squares loss is proposed for ranking in this paper. The implementation of this algorithm is simple, and an expression of the solution is derived via a sampling operator and an integral operator. An explicit convergence rate for leaning a ranking function is given in terms of the suitable choices of the step size and the regularization parameter. The analysis technique used here is capacity independent and is novel in error analysis of ranking learning. Experimental results on real-world data have shown the effectiveness of the proposed algorithm in ranking tasks, which verifies the theoretical analysis in ranking error.
|Alternate Journal||IEEE Trans Cybern|