arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.04718math.OCstat.COstat.ML
收藏

局部几何和批量对非凸问题随机梯度下降的影响

The Impact of Local Geometry and Batch Size on Stochastic Gradient Descent for Nonconvex Problems

Vivak Patel

摘要:

在机器学习中非凸最优化问题的几个实验报告中,观察到随机梯度下降(SGD)与更确定性的方法相比更喜欢具有平坦盆地的最小值,但对这种现象的严格理解很少。事实上,缺乏这样的工作导致了一个未经验证的,但被广泛接受的随机机制,描述了为什么SGD更喜欢平坦的极小化,而不是尖锐的极小化。然而,正如我们所证明的,随机机制无法解释这种现象。在这里,我们提出了一个替代的确定性机制,可以准确地解释为什么SGD喜欢平坦的最小化尖锐的最小化。我们推导出这种机制的基础上详细分析了一个通用的随机二次问题,它概括了经典梯度下降的已知结果。最后,我们验证了我们的确定性机制的两个非凸问题的预测。

英文摘要:

In several experimental reports on nonconvex optimization problems in machine learning, stochastic gradient descent (SGD) was observed to prefer minimizers with flat basins in comparison to more deterministic methods, yet there is very little rigorous understanding of this phenomenon. In fact, the lack of such work has led to an unverified, but widely-accepted stochastic mechanism describing why SGD prefers flatter minimizers to sharper minimizers. However, as we demonstrate, the stochastic mechanism fails to explain this phenomenon. Here, we propose an alternative deterministic mechanism that can accurately explain why SGD prefers flatter minimizers to sharper minimizers. We derive this mechanism based on a detailed analysis of a generic stochastic quadratic problem, which generalizes known results for classical gradient descent. Finally, we verify the predictions of our deterministic mechanism on two nonconvex problems.

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。

↑