Answers are grounded in this paper and cite their sources.
The selection of the penalty functional is critical for the performance of a regularized learning algorithm, and thus lq-regularizer (1 ≤ q ≤ 2) deserves special attention. We consider the regularized least-squares regression learning algorithm for the non-identical and weakly dependent samples. The dependent samples satisfy the polynomially β-mixing condition and the sequence of the non-identical sampling marginal measures converges to a probability measure exponentially in the dual of a Hölder space. We conduct the rigorous unified error analysis and derive the satisfactory learning rates of the algorithm by the stepping stone technique in the error decomposition and the independent-blocks technique in the sample error estimates.
No takes yet. Share an insight, caveat, or question.
Guo et al. (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: