基于随机逼近的退火优化渐进学习
Annealing Optimization for Progressive Learning with Stochastic Approximation
AI总结:
本文提出一种基于退火优化的在线无梯度随机逼近学习算法,构建可解释且渐进增长的竞争性神经网络,适用于监督、无监督和强化学习,实现性能与复杂度的在线权衡及收敛性分析。
摘要:
本文提出了一种学习模型,旨在满足计算资源有限且优先考虑鲁棒性和可解释性的应用需求。学习问题可被表述为受约束的随机优化问题,其中约束主要来源于定义复杂度与性能之间权衡的模型假设。这种权衡与过拟合、泛化能力以及对噪声和对抗攻击的鲁棒性密切相关,并且既取决于模型的结构和复杂度,也取决于所用优化方法的性质。我们开发了一种基于退火优化的在线原型学习算法,该算法被表述为在线无梯度随机逼近算法。该学习模型可被视为一个可解释且渐进增长的竞争性学习神经网络模型,适用于监督学习、无监督学习和强化学习。算法的退火特性有助于实现超参数调优需求最小化、防止陷入不良局部最小值,并对初始条件具有鲁棒性。同时,它通过一种直观的分岔现象,按需渐进增加学习模型的复杂度,从而在线控制性能与复杂度之间的权衡。最后,随机逼近的使用使得能够通过动力系统和控制中的数学工具研究学习算法的收敛性,并允许其与强化学习算法集成,构建自适应的状态-动作聚合方案。
英文摘要:
In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained stochastic optimization problems, with the constraints originating mainly from model assumptions that define a trade-off between complexity and performance. This trade-off is closely related to over-fitting, generalization capacity, and robustness to noise and adversarial attacks, and depends on both the structure and complexity of the model, as well as the properties of the optimization methods used. We develop an online prototype-based learning algorithm based on annealing optimization that is formulated as an online gradient-free stochastic approximation algorithm. The learning model can be viewed as an interpretable and progressively growing competitive-learning neural network model to be used for supervised, unsupervised, and reinforcement learning. The annealing nature of the algorithm contributes to minimal hyper-parameter tuning requirements, poor local minima prevention, and robustness with respect to the initial conditions. At the same time, it provides online control over the performance-complexity trade-off by progressively increasing the complexity of the learning model as needed, through an intuitive bifurcation phenomenon. Finally, the use of stochastic approximation enables the study of the convergence of the learning algorithm through mathematical tools from dynamical systems and control, and allows for its integration with reinforcement learning algorithms, constructing an adaptive state-action aggregation scheme.
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。