Despite the evolution of Convolutional Neural Networks (CNNs), their performance is surprisingly dependent on the choice of hyperparameters. However, it remains challenging to efficiently explore large hyperparameter search space due to the long training times of modern CNNs. Multi-fidelity optimization enables the exploration of more hyperparameter configurations given budget by early termination of unpromising configurations. However, it often results in selecting a sub-optimal configuration as training with the high-performing configuration typically converges slowly in an early phase. In this paper, we propose Multi-fidelity Optimization with a Recurring Learning rate (MORL) which incorporates CNNs' optimization process into multi-fidelity optimization. MORL alleviates the problem of slow-starter and achieves a more precise low-fidelity approximation. Our comprehensive experiments on general image classification, transfer learning, and semi-supervised learning demonstrate the effectiveness of MORL over other multi-fidelity optimization methods such as Successive Halving Algorithm (SHA) and Hyperband. Furthermore, it achieves significant performance improvements over hand-tuned hyperparameter configuration within a practical budget.
翻译:尽管进化神经网络(CNNs)不断演变,但其性能却令人惊讶地取决于超参数的选择。然而,由于现代CNN的训练时间很长,有效探索大型超光度搜索空间仍然具有挑战性。多纤维优化使得能够探索通过早期终止不前景配置而得到的预算中更多的超光度配置。然而,它往往导致选择一个亚优度配置,因为与高性能配置的培训通常在早期阶段缓慢地交汇。我们在本文件中提议采用累进学习率(MORL)实现多纤维优化,将CNN的优化进程纳入多纤维优化。MOR缓解了启动速度缓慢的问题,并实现了更精确的低纤维近似值。我们在一般图像分类、转移学习和半超强学习方面的全面实验表明MOL相对于其他多纤维优化方法(如Condivive Algorithm(SHA)和超频频谱)的有效性。此外,它实现了大幅的超实际超软化的超硬化预算性能改进。