On The Power of Curriculum Learning in Training Deep Networks
This addresses the challenge of efficient training for deep learning practitioners, but it is incremental as it builds on existing curriculum learning concepts with new methods and analysis.
The paper tackles the problem of training deep networks by analyzing curriculum learning, which involves non-uniform sampling of mini-batches based on difficulty, and finds that it increases learning speed and improves final performance on test data, with empirical evaluation showing benefits across various architectures and datasets like CIFAR-10, CIFAR-100, and ImageNet subsets.
Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform sampling of mini-batches, on the training of deep networks, and specifically CNNs trained for image recognition. To employ curriculum learning, the training algorithm must resolve 2 problems: (i) sort the training examples by difficulty; (ii) compute a series of mini-batches that exhibit an increasing level of difficulty. We address challenge (i) using two methods: transfer learning from some competitive ``teacher" network, and bootstrapping. In our empirical evaluation, both methods show similar benefits in terms of increased learning speed and improved final performance on test data. We address challenge (ii) by investigating different pacing functions to guide the sampling. The empirical investigation includes a variety of network architectures, using images from CIFAR-10, CIFAR-100 and subsets of ImageNet. We conclude with a novel theoretical analysis of curriculum learning, where we show how it effectively modifies the optimization landscape. We then define the concept of an ideal curriculum, and show that under mild conditions it does not change the corresponding global minimum of the optimization function.