资源分类
》 资源 》论文》Stochastic Dual Coordinate Ascent with Adaptive Probabilities

Stochastic Dual Coordinate Ascent with Adaptive Probabilities

2020-03-05 | |  51 |   34 |   0

Abstract

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method to adaptively change the probability distribution over the dual variables throughout the iterative process. AdaSDCA achieves provably better complexity bound than SDCA with the best fixed probability distribution, known as importance sampling. However, it is of a theoretical character as it is exp sive to implement. We also propose AdaSDCA+: a practical variant which in our experiments outperforms existing non-adaptive methods.

上一篇：Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs

下一篇：Spectral MLE: Top-K Rank Aggregation from Pairwise Comparisons

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...