arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09490cs.LGstat.ML
收藏

具有隐藏低秩结构的随机线性Bands

Stochastic Linear Bandits with Hidden Low Rank Structure

California Institute of Technology(加州理工学院);University of California, Irvine(加州大学欧文分校)

Sahin Lale, Kamyar Azizzadenesheli, Anima Anandkumar, Babak Hassibi

摘要:

高维表示通常具有较低维的底层结构。在许多决策制定过程中尤其如此。例如,当从深度神经网络生成动作的表示时,期望低秩结构是合理的,而像稀疏性这样的传统结构不再有效。子空间恢复方法,如主成分分析(PCA),可以发现潜在的低秩结构的特征空间,降低学习任务的复杂性。在这项工作中,我们提出了投影随机线性强盗(PSLB),高维随机线性强盗(SLB)的行动时,表示有一个底层的低维子空间结构的算法。PSLB部署基于PCA的投影迭代地找到SLB中的低秩结构。我们表明,部署投影方法,确保降维和结果在一个更严格的遗憾的上界,是在子空间的维数和它的属性,而不是周围空间的维数。我们将图像分类任务修改为SLB设置,并根据经验表明,当预先训练的DNN提供高维特征表示时,与最先进的算法相比,部署PSLB会显著减少遗憾并更快地收敛到准确的模型。

英文摘要:

High-dimensional representations often have a lower dimensional underlying structure. This is particularly the case in many decision making settings. For example, when the representation of actions is generated from a deep neural network, it is reasonable to expect a low-rank structure whereas conventional structures like sparsity are not valid anymore. Subspace recovery methods, such as Principle Component Analysis (PCA) can find the underlying low-rank structures in the feature space and reduce the complexity of the learning tasks. In this work, we propose Projected Stochastic Linear Bandit (PSLB), an algorithm for high dimensional stochastic linear bandits (SLB) when the representation of actions has an underlying low-dimensional subspace structure. PSLB deploys PCA based projection to iteratively find the low rank structure in SLBs. We show that deploying projection methods assures dimensionality reduction and results in a tighter regret upper bound that is in terms of the dimensionality of the subspace and its properties, rather than the dimensionality of the ambient space. We modify the image classification task into the SLB setting and empirically show that, when a pre-trained DNN provides the high dimensional feature representations, deploying PSLB results in significant reduction of regret and faster convergence to an accurate model compared to state-of-art algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑