arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.01744stat.MLcs.LG
收藏

稀疏伊辛模型的样本有效L0-L2约束结构学习

Sample-Efficient L0-L2 Constrained Structure Learning of Sparse Ising Models

Vicarious AI

Antoine Dedieu, Miguel Lázaro-Gredilla, Dileep George

摘要:

考虑了从$n$ i.i.d.学习具有$p$节点的稀疏伊辛模型的基础图的问题。样品最新和最好的方法结合了经验损失(逻辑斯谛回归损失或相互作用筛选损失)与正则化(L1罚分或L1约束)。这导致了一个凸问题,可以为图的每个节点单独解决。在这项工作中,我们利用基数约束L0范数,这是已知的适当诱导稀疏性,并进一步将其与L2范数结合起来,以更好地模拟非零系数。我们表明,我们提出的估计实现了改进的样本复杂性,(a)理论上,达到新的国家的最先进的上限恢复保证,和(b)经验上,通过显示更尖锐的相变之间的穷人和完全恢复的图拓扑结构在文献中研究,当比较他们的L1为基础的国家的最先进的方法。

英文摘要:

We consider the problem of learning the underlying graph of a sparse Ising model with $p$ nodes from $n$ i.i.d. samples. The most recent and best performing approaches combine an empirical loss (the logistic regression loss or the interaction screening loss) with a regularizer (an L1 penalty or an L1 constraint). This results in a convex problem that can be solved separately for each node of the graph. In this work, we leverage the cardinality constraint L0 norm, which is known to properly induce sparsity, and further combine it with an L2 norm to better model the non-zero coefficients. We show that our proposed estimators achieve an improved sample complexity, both (a) theoretically, by reaching new state-of-the-art upper bounds for recovery guarantees, and (b) empirically, by showing sharper phase transitions between poor and full recovery for graph topologies studied in the literature, when compared to their L1-based state-of-the-art methods.

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。

↑