arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.04392math.OCstat.ML
收藏

一种用于光滑随机优化的回顾近似方法

A Retrospective Approximation Approach for Smooth Stochastic Optimization

David Newton, Raghu Bollapragada, Raghu Pasupathy, Nung Kwan Yip

AI总结:

针对随机梯度法单步更新的局限,提出回顾近似框架,支持即插即用确定性求解器并按需终止,建立了收敛性与复杂度理论,实验显示其可免去超参数调优。

摘要:

随机梯度(SG)是求解具有光滑(非凸)目标函数$f$和随机一阶预言机的随机优化(SO)问题的主流迭代技术。SG的吸引力部分源于其简单性:沿负子采样梯度方向执行单步更新来迭代当前解。本文对SG在子采样更新间仅执行单步而非多步的选择提出了质疑。我们的研究自然引出将SG推广为回顾近似(Retrospective Approximation,RA)框架:在每次迭代中,一个“确定性求解器”在子采样的确定性问题上可执行多步操作,并在从统计效率角度判断无需继续求解时停止。RA因此让实际应用中颇具吸引力的思路变得严谨——每次迭代中“即插即用”现有求解器(例如L-BFGS线搜索或Newton-CG),且仅在必要程度内求解。我们以观测梯度的相对误差为核心分析对象建立了完整理论,证明当样本量以合适速率增长时,RA在极弱条件下仍能保持几乎必然收敛性和$L_1$一致性。我们还刻画了RA的迭代复杂度和预言机复杂度(针对线性和次线性求解器),并提出了一种能达到最优复杂度速率的实用终止准则。为涵盖非凸$f$的情形,我们提出了一种“随机中心极限定理”,该定理纳入了所有一阶临界点处的曲率影响,证明其渐近行为可由某种正态混合分布描述。我们的数值实验结果表明,RA能够策略性地整合现有二阶确定性求解器,这一特性对于免去超参数调优可能具有重要意义。

英文摘要:

Stochastic Gradient (SG) is the defacto iterative technique to solve stochastic optimization (SO) problems with a smooth (non-convex) objective $f$ and a stochastic first-order oracle. SG's attractiveness is due in part to its simplicity of executing a single step along the negative subsampled gradient direction to update the incumbent iterate. In this paper, we question SG's choice of executing a single step as opposed to multiple steps between subsample updates. Our investigation leads naturally to generalizing SG into Retrospective Approximation (RA) where, during each iteration, a "deterministic solver" executes possibly multiple steps on a subsampled deterministic problem and stops when further solving is deemed unnecessary from the standpoint of statistical efficiency. RA thus rigorizes what is appealing for implementation -- during each iteration, "plug in" a solver, e.g., L-BFGS line search or Newton-CG, as is, and solve only to the extent necessary. We develop a complete theory using relative error of the observed gradients as the principal object, demonstrating that almost sure and $L_1$ consistency of RA are preserved under especially weak conditions when sample sizes are increased at appropriate rates. We also characterize the iteration and oracle complexity (for linear and sub-linear solvers) of RA, and identify a practical termination criterion leading to optimal complexity rates. To subsume non-convex $f$, we present a certain "random central limit theorem" that incorporates the effect of curvature across all first-order critical points, demonstrating that the asymptotic behavior is described by a certain mixture of normals. The message from our numerical experiments is that the ability of RA to incorporate existing second-order deterministic solvers in a strategic manner might be important from the standpoint of dispensing with hyper-parameter tuning.

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。

↑