RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks
arXiv:2005.05955
Abstract
We propose RSO (random search optimization), a gradient free Markov Chain Monte Carlo search based approach for training deep neural networks. To this end, RSO adds a perturbation to a weight in a deep neural network and tests if it reduces the loss on a mini-batch. If this reduces the loss, the weight is updated, otherwise the existing weight is retained. Surprisingly, we find that repeating this process a few times for each weight is sufficient to train a deep neural network. The number of weight updates for RSO is an order of magnitude lesser when compared to backpropagation with SGD. RSO can make aggressive weight updates in each step as there is no concept of learning rate. The weight update step for individual layers is also not coupled with the magnitude of the loss. RSO is evaluated on classification tasks on MNIST and CIFAR-10 datasets with deep neural networks of 6 to 10 layers where it achieves an accuracy of 99.1% and 81.8% respectively. We also find that after updating the weights just 5 times, the algorithm obtains a classification accuracy of 98% on MNIST.
arXiv commentTechnical Report
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Neural Architecture Search with Reinforcement Learning
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Pruning Filters for Efficient ConvNets
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
- Gradient Descent Provably Optimizes Over-parameterized Neural Networks
- Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
- Training Neural Networks Without Gradients: A Scalable ADMM Approach
- Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs