arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.02839cs.LGmath.OCstat.ML
收藏

无模型超参数化非对称矩阵分解中的算法正则化

Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization

Cornell University(康奈尔大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Liwei Jiang, Yudong Chen, Lijun Ding

AI总结:

该研究针对无模型超参数化非对称矩阵分解的过拟合问题,证明带小随机初始化的普通梯度下降结合早停可无需显式正则化得到最优低秩近似,给出了更宽松的复杂度界,且理论与数值实验吻合。

摘要:

我们研究了具有任意超参数化的自然非凸公式下的非对称矩阵分解问题。本文考虑无模型设定,对观测矩阵的秩或奇异值仅做最低限度假设,该设定下全局最优解已被证明会过拟合。我们证明,采用小随机初始化的普通梯度下降会依次恢复观测矩阵的主成分。因此,当配备合适的早停策略时,梯度下降无需显式正则化就能生成观测矩阵的最优低秩近似。我们对近似误差、迭代复杂度、初始化规模和步长之间的关系给出了精确刻画。我们的复杂度界几乎与维度无关,且与近似误差呈对数关系,与现有工作相比,对步长和初始化的要求显著宽松。我们的理论结果可准确预测梯度下降的行为,与数值实验结果吻合良好。

英文摘要:

We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization. The model-free setting is considered, with minimal assumption on the rank or singular values of the observed matrix, where the global optima provably overfit. We show that vanilla gradient descent with small random initialization sequentially recovers the principal components of the observed matrix. Consequently, when equipped with proper early stopping, gradient descent produces the best low-rank approximation of the observed matrix without explicit regularization. We provide a sharp characterization of the relationship between the approximation error, iteration complexity, initialization size and stepsize. Our complexity bound is almost dimension-free and depends logarithmically on the approximation error, with significantly more lenient requirements on the stepsize and initialization compared to prior work. Our theoretical results provide accurate prediction for the behavior gradient descent, showing good agreement with numerical experiments.

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。

↑